CN108735270A - Blood flow reserve score acquisition methods, device, system and computer storage media based on dimensionality reduction model - Google Patents
Blood flow reserve score acquisition methods, device, system and computer storage media based on dimensionality reduction model Download PDFInfo
- Publication number
- CN108735270A CN108735270A CN201810516585.0A CN201810516585A CN108735270A CN 108735270 A CN108735270 A CN 108735270A CN 201810516585 A CN201810516585 A CN 201810516585A CN 108735270 A CN108735270 A CN 108735270A
- Authority
- CN
- China
- Prior art keywords
- coronary artery
- blood flow
- dimensionality reduction
- cross
- reduction model
- 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
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/40—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for data related to laboratory analysis, e.g. patient specimen analysis
Abstract
The invention discloses blood flow reserve score acquisition methods, device, system and computer storage media based on dimensionality reduction model, wherein method includes：Step S1 obtains and handles coronary artery medical image, obtains the dimensionality reduction model of expression coronary artery geometry topological structure, and the dimensionality reduction model includes the cross-sectional area of center line vector sum coronary artery coronarius everywhere；Step S2 obtains coronary artery related physiological parameters, and resistance coefficient of the coronary artery to blood flow is calculated according to dimensionality reduction model；Step S3, according in coronary artery blood flow flow and the resistance coefficient, calculate pressure value everywhere in coronary artery；The blood flow reserve score of corresponding position is calculated based on the pressure value in coronary artery everywhere in step S4.The present invention establishes the dimensionality reduction model of coronary artery using coronary artery medical image, obtains blood flow reserve score in real time according to Hemodynamics calculating, while ensureing accuracy, greatly improves operation efficiency.
Description
Technical field
The present invention relates to field of medical technology, and in particular to a kind of blood flow reserve based on coronary artery dimensionality reduction model
Score acquisition methods, device, system and computer storage media.
Background technology
The main reason for atherosclerosis is coronary heart disease, cerebral infarction and peripheral vascular disease seriously affects the body of people
Body Health and Living quality.For hat venereal disease diagnosis, angiography of coronary arteries is considered as " goldstandard ", but this
Method can only evaluation of vascular diseases become position stenosis, can not influence of the quantitative assessment hemadostewnosis to physiological function, may
Over-evaluate the severity for either underestimating lesion and then over-treatment or lesion is caused not to handle.Present medical diagnosis is coronal
The generally acknowledged index of arteriarctia is blood flow reserve score (FFR), and the definition of blood flow reserve score is：In coronary artery, there are narrow
In the case of lesion, the distal vessels of the coronary artery stenosis lesion can be obtained maximum blood flow and when institute under normal condition
The ratio of obtainable maximum blood flow.
In the prior art, generally use intrusive mood is tested to obtain FFR, for example, diagnostic cardiac catheterization, performed the operation
Journey includes：Conventional angiography of coronary arteries (CCA) is carried out so that coronary artery pathological changes visualize, while intravenously using gland
Glycosides induction (coronary artery be in maximum congestive state), calculate the coronary artery stenosis distal end pressure that is obtained by pressure transducer with
The ratio of heart aorta pressure determines FFR.Intrusive mood test can cause patient body wound, increase operation risk and control
Treatment expense.
The risk and expensive expense that intervention diagnosis is brought can be then avoided by numerical simulation calculation FFR, carry out Numerical-Mode
When quasi- calculating, patient data (such as CT, MRI, DSA etc.) is acquired by high-definition image equipment first, then to patient vessel's mould
Type is reconstructed, and carrys out the blood flow situation in simulated blood vessel in conjunction with Fluid Mechanics Computation (CFD) method.According to clinical data pair
Than noninvasive FFR is highly effective to the diagnosis of myocardial ischemia, while also more more acurrate than imaging evaluation.
In general, the calculating of non-intrusion type blood flow reserve score is carried out based on threedimensional model, the blood of blood vessel regional area is studied
Stream needs the solution for carrying out flow equation to the element of volume in whole region to integrate after solving convergence and extract required pressure
The information such as power distribution, taking can be longer.
Invention content
The blood flow reserve score acquisition methods that the present invention provides a kind of based on coronary artery dimensionality reduction model, device and
System establishes the dimensionality reduction model of coronary artery using coronary artery medical image, and real-time obtain is calculated according to Hemodynamics
To blood flow reserve score operation efficiency is greatly improved while ensureing accuracy.
A method of blood flow reserve score is obtained based on coronary artery dimensionality reduction model, including：
Step S1 obtains and handles coronary artery medical image, obtains the dimensionality reduction of expression coronary artery geometry topological structure
Model, the dimensionality reduction model include the cross-sectional area of center line vector sum coronary artery coronarius everywhere；
Step S2 obtains coronary artery related physiological parameters, and calculates coronary artery to blood flow according to dimensionality reduction model
Resistance coefficient；
Step S3, according in coronary artery blood flow flow and the resistance coefficient, calculate in coronary artery everywhere
Pressure value；
The blood flow reserve score of corresponding position is calculated based on the pressure value in coronary artery everywhere in step S4.
The coronary artery medical image includes but not limited to using CT (i.e. CT scan), MRI (i.e. magnetic
Resonance image-forming), DSA (i.e. Digital subtraction angiograph) obtain image, can obtain coronarius three according to these images
Tie up structural information.
Include still three dimensions geological information coronarius in heretofore described dimensionality reduction model, but by coronary artery
Each branch be reduced to one-dimensional linear structure, to improve the computational efficiency of blood flow reserve score.
Connection relation and space bit between each branch of coronary artery can be obtained according to center line vector coronarius
Relationship is set, skeleton structure coronarius is obtained.
In step S2, the coronary artery moves towards the resistance coefficient of blood flow and the angle of vascular bifurcation center line,
Centerline length between the cross-sectional area of blood vessel and two bifurcations is related, and the prior art can be used in calculating process.
In step S3, prior art acquisition may be used in the blood flow flow in coronary artery, for example, being surveyed using Doppler method
Amount arteria carotis communis volume flow rate and colored quantitative velocity imaging (CVI-Q) method measure.
The center line vector is the vector of each main coronary artery of characterization and the center line of branch, according to center line to
Amount can obtain the space trend of main coronary artery and branch.
Coronary artery medical image and coronary artery related physiological parameters can obtain simultaneously, non-concurrent can also obtain.
The coronary artery related physiological parameters include at least physiological parameter involved in calculating process, including but not limited to：Physiology
Medical test results (such as：Cardiac cycle, blood pressure, blood flow, hemoglobin, blood platelet, electrocardiogram, gene, family's medical history etc.
Deng), image data/segmentation data/reconstruct geometric data (narrow location, narrow length, stenosed section, calcified plaque, heart ruler
It is very little, coronary arterial tree and topological structure etc.).
A variety of methods may be used in the structure of the dimensionality reduction model, and one of which is suitable for CT (i.e. electronic computer tomographies
Scanning), MRI (i.e. magnetic resonance imaging), the method for DSA (i.e. Digital subtraction angiograph) image it is as follows：
The construction method of the dimensionality reduction model, including：
Step S1-1-1, chooses entrance coronarius as initial position in the coronary artery medical image,
Initial position obtains the cross section of coronary artery inlet, using the geometric center of gravity of cross section as the central point of the cross section,
Two orthogonal feature vectors are determined using central point as origin, the friendship according to two feature vectors and coronary artery periphery
Point determines initial position cross-sectional area coronarius；
Step S1-1-2, along the direction both perpendicular to two feature vectors, with two features of pre- fixed step size synchronous translational
Vector determines the transversal of corresponding position coronary artery cross section according to the intersection point of two feature vectors and coronary artery periphery
Area, using the geometric center of gravity of cross section as the central point of coronary artery cross section at this；
Step S1-1-3 determines bifurcation coronarius according to the changing value of cross-sectional area, at two bifurcations
Center position determine center line vector, establish according to center line vector sum coronary artery cross-sectional area everywhere described in
Dimensionality reduction model.
Preferably, in step S1-1-1 and step S1-1-2, coronary artery periphery is obtained using edge detection, at two
On the direction of feature vector, the diameter of coronary artery periphery is respectively d2And d3, rp=(d2+d3)/4, d2And d3The center of circle overlap
By coronary artery periphery be approximately using point O it is the center of circle with r for point OpCross-sectional area is calculated for the circle of radius.
Preferably, in step S1-1-3, if it is determined that factor g > 1.9, then be coronal between cross section at coronary artery two
The bifurcation of artery, judgement factor g=max { d2, d3}/min{d2, d3}。
Another kind is suitable for CT (i.e. CT scan), MRI (i.e. magnetic resonance imaging), DSA (i.e. digital outline
Angiography) image dimensionality reduction model construction method it is as follows：
The construction method of the dimensionality reduction model, including：
Step S1-2-1 pre-processes the coronary artery medical image, obtains binary image；
Step S1-2-2 carries out micronization processes to binary image, obtains center line vector coronarius；
Step S1-2-3 traverses coronary artery along the center line vector, using center line everywhere unit vector as transversal
The normal vector in face does cross section to coronary artery, and the boundary of coronary artery cross section is determined according to gray threshold, to cross section into
Row integral obtains the cross-sectional area of coronary artery corresponding position, according to the cross section of the center line vector sum coronary artery everywhere
Product establishes the dimensionality reduction model.
Preferably, in step S1-2-1, the coronary artery medical image includes multiple two dimensional gray distribution maps, according to
Slice is ranked sequentially each image, and following processing is done for each image：
Step S1-2-1-1 is based on the corresponding substrate image of each image creation, and each region has difference in substrate image
Gray threshold；
Step S1-2-1-2 carries out binary conversion treatment to corresponding projected image using substrate image, obtains projected image
Binary image；
Step S1-2-1-3 builds the binary picture of coronary artery medical image using the binary image of each image
Picture.
The present invention also provides a kind of computer readable storage medium, the computer-readable recording medium storage has calculating
Machine program, the computer program are subsequently can by computer being obtained based on coronary artery dimensionality reduction model described in realization when device executes
The method for taking blood flow reserve score.
The present invention also provides a kind of devices obtaining blood flow reserve score, including computer storage, computer disposal
Device and it is stored in the computer program that can be executed in the computer storage and on the computer processor, it is described
When computer processor executes the computer program, realizes and described blood flow storage is obtained based on coronary artery dimensionality reduction model
The method of back-up number.
The present invention also provides a kind of system obtaining blood flow reserve score, including terminal and server, the services
Device includes computer storage, computer processor and is stored in the computer storage and can be in the computer
The computer program executed on processor, the server obtains coronary artery medical image from terminal and coronary artery is related
Physiological parameter；When the computer processor executes the computer program, the side of the acquisition blood flow reserve score is realized
Method.
The terminal and server is communicated by wired or wireless way, and the terminal is usually provided at medical services machine
Structure can upload coronary artery medical image by terminal to server, and the server is generally arranged at third party's service machine
Structure carries out analyzing processing to coronary artery medical image, obtains blood flow reserve score and feed back to terminal, is medical treatment patient
The diseases such as myocardial ischemia provide fast and accurately foundation.
The software section of terminal and server uses C, C++, Java, the exploitation of the programming languages such as Pyho, HTM5 to complete.
Blood flow reserve score acquisition methods provided by the invention based on coronary artery dimensionality reduction model, device and it is
System establishes the dimensionality reduction model of coronary artery using coronary artery medical image, is obtained in real time according to Hemodynamics calculating
Blood flow reserve score, while ensureing accuracy, the CPU calculating times are about reduced to 1/10th needed for the prior art.
Description of the drawings
Fig. 1 is that the present invention is based on the flow charts of the blood flow reserve score acquisition methods of coronary artery dimensionality reduction model；
In Fig. 2, (a) is coronary artery medical image, is (b) coronary artery figure；(c) coronary artery dimensionality reduction model；
Fig. 3 is to be established in dimensionality reduction model process in embodiment 1, the position relationship of two feature vectors and coronary artery
Schematic diagram；
Fig. 4 is coronary artery overall network figure；
Fig. 5 is the blood flow profile of flowrate of a cardiac cycle, as coronary artery inlet blood under different HR Heart Rates
The input value of flow velocity degree；
Fig. 6 is the model schematic of coronary artery stenosis.
Specific implementation mode
Below in conjunction with the accompanying drawings, to the present invention is based on the blood flow reserve score acquisition methods of coronary artery dimensionality reduction model and
System is described in detail.
Embodiment 1
As shown in Figure 1, a kind of method that blood flow reserve score is obtained based on coronary artery dimensionality reduction model, including：
Step S1 obtains and handles coronary artery medical image, obtains the dimensionality reduction of expression coronary artery geometry topological structure
Model, the dimensionality reduction model include the cross-sectional area of center line vector sum coronary artery coronarius everywhere.
Coronary artery medical image includes but not limited to using CT (i.e. CT scan), MRI (i.e. magnetic resonance
Imaging), the images that obtain of DSA (i.e. Digital subtraction angiograph), it is four-dimensional that expression-form is not limited to two dimension, three peacekeepings, according to being preced with
Shape artery medical image can obtain three-dimensional structure information coronarius, the image data lattice of coronary artery medical image
Formula is not limited to Dicom files.
As shown in Fig. 2, (a) is three-dimensional coronary artery medical image in Fig. 2, it is (b) coronary artery figure；(c) coronal dynamic
Arteries and veins dimensionality reduction model.Include the spatial relation of each branch of coronary artery in dimensionality reduction model coronarius, but will be coronal dynamic
Each branch of arteries and veins is reduced to one-dimensional linear structure, i.e., the position of each bifurcation and spatial relation and is moved with coronal in figure (a)
Bifurcation information is consistent in arteries and veins medical image, reaches branch using single line segment table between two neighboring bifurcation.
The blood vessel volume elements of the brightness ratio of cholesterol plaques is much bigger, in order to improve the accuracy of dimensionality reduction model construction, into
Before the structure of row dimensionality reduction model, cholesterol plaques are blocked.
The construction method of dimensionality reduction model, including：
Step S1-1-1, chooses entrance coronarius as initial position in the coronary artery medical image,
Initial position obtains the cross section of coronary artery inlet, using the geometric center of gravity of cross section as the central point of the cross section,
Two orthogonal feature vectors are determined using central point as origin, the friendship according to two feature vectors and coronary artery periphery
Point determines initial position cross-sectional area coronarius.
The profile of coronary artery periphery namely vascular wall coronarius, on coronary artery medical image, coronary artery
Vascular wall has significant change compared to other regional luminances, and coronary artery circumferential position can be obtained by detecting brightness change.
As shown in figure 3, two orthogonal feature vectors are respectively v2And v3, on the direction of two feature vectors, hat
The diameter of shape periarterial is respectively d2 and d3, rpIt is point O that the center of circle of=(d2+d3)/4, d2 and d3, which overlaps, will be outside coronary artery
It is the center of circle with r that week, which is approximately using point O,pCross-sectional area is calculated for the circle of radius.
Step S1-1-2, along the direction both perpendicular to two feature vectors, with two features of pre- fixed step size synchronous translational
Vector determines the transversal of corresponding position coronary artery cross section according to the intersection point of two feature vectors and coronary artery periphery
Area, using the geometric center of gravity of cross section as the central point of coronary artery cross section at this.
Both perpendicular to the direction of two feature vectors, i.e. vector v in figure1Indicated direction, vector v1Instruction direction
It is consistent with extending direction coronarius.Along vector v1Direction with two feature vectors of pre- fixed step size synchronous translational, such as just
Beginning position is position 1, after pre- fixed step size synchronous translational, in-position 2 and position 3 successively, and respectively at position 2 and position 3,
Calculate the central point and cross-sectional area of corresponding coronary artery cross section.
The geometric center of gravity of cross section is the central point of cross section, and the algorithm of cross-sectional area is referring to the transversal of initial position
Face algorithm.
The more short then counting accuracy of pre- fixed step size is higher, and pre- fixed step size more long then operation time is shorter, actual predetermined step
Long tradeoff computational accuracy and operation time obtain.
Pre- fixed step size can select as needed, may be the same or different at different zones, for example, coronal
The larger crooked position of artery curvature, the shorter pre- fixed step size of setting；In the smaller crooked position of coronary artery curvature, setting compared with
Long pre- fixed step size.
Step S1-1-3 determines bifurcation coronarius according to the changing value of cross-sectional area, at two bifurcations
Center position determine center line vector, establish dimensionality reduction mould according to the cross-sectional area of center line vector sum coronary artery everywhere
Type.
In the present embodiment, it is first determined then bifurcation coronarius obtains branch vessel by starting point of bifurcation
Center line and cross-sectional area (the step of obtaining center line and cross-sectional area with main coronary artery blood vessel (i.e. step S1-1-
1) equally).
According on two feature vector directions, diameter calculation coronarius judges factor g, judgement factor g=max { d2,
d3}/min{d2, d3, if it is determined that factor g > 1.9, then be bifurcation coronarius between cross section at coronary artery two,
Step S2 obtains coronary artery related physiological parameters, and calculates coronary artery to blood flow according to dimensionality reduction model
Resistance coefficient.
Step S3 calculates blood everywhere in coronary artery according to the blood flow flow and resistance coefficient in coronary artery
Pressure value.
Coronary artery includes to the resistance coefficient of blood flow：Resistance coefficient at coronary artery bifurcation, and
Resistance coefficient between two bifurcations, the calculating of resistance coefficient is referring to document：Chnafa C,Valen-Sendstad K,Brina
O,et al.Improved reduced-order modelling of cerebrovascular flow distribution
by accounting for arterial bifurcation pressure drops[J].Journal of
biomechanics,2017,51:83-88。
The main process of step S2 and step S3 includes：
First, each branch in coronary artery dimensionality reduction model is divided into several segmentations, fluid is established for each segmentation
Governing equation and boundary control equations, it is as follows respectively：
Fluid governing equation：
In formula：Sk：The vascular cross-section product being segmented for k-th；
uk：The mean blood flow velocity being segmented for k-th；
ρ：For blood flow density；
Indicate external force, such as gravity, frictional force etc. suffered by blood vessel；
x：Indicate disalignment distance；
t：Indicate the time.
Boundary control equations：
pk：Indicate the pressure p on k-th of segmented vessel；
ρ：Blood flow density；
ck：Indicate the blood vessel elasticity modulus of k-th of segmentation, rule of thumb formula obtains；
f(Sk)：It indicates and the relevant specific function of vascular cross-section.
Equation (1) (2) (3) is referring to document：T.M.Gamilov,P.Kopylov,R.Pryamonosov,S.Simakov,
Virtual fractional flow reserve assessment in patient-specific coronary
networks by 1D hemodynamic model,Russ.J.Numer.Anal.Math.Modelling 2015；30(5):
269–276。
The resistance R of blood flow branch section (i.e. branch between two bifurcations)kCome from：The resistance that blood flow is generated along blood flow
Force coefficient R1With the resistance coefficient R of coronary arterial tree2, specifically, for the blood vessel containing branch, resistance coefficient Rk=
R1+R2, for the blood vessel not comprising branch, resistance coefficient Rk=R1。
In formula, R1The resistance coefficient generated along blood flow for blood flow；
μ is mean blood flow velocity；
LkFor the blood flow paths length of branch section；
Lk=∑si||δi|| (5)
δiFor the link vector of the i-th node and i+1 node of k-th of segmented vessel center line；
rkIt is the mean radius of branch section blood vessel：
δiFor the link vector of the i-th node and i+1 node of k-th of segmentation section vessel centerline；
riFor the radius of the blood vessel at node i.
In the resistance coefficient R that calculating blood flow is generated in coronary artery crotch2When, ρ is the density of blood flow, QdatAnd rdatPoint
Not Wei branch blood flow flow and radius, angle of the upstream and downstream blood vessel at bifurcation is αDat, k。
Equation (4) (5) (6) (7) (8) is referring to document：Chnafa C,Valen-Sendstad K,Brina O,et
al.Improved reduced-order modelling of cerebrovascular flow distribution by
accounting for arterial bifurcation pressure drops[J].Journal of
biomechanics,2017,51:83-88。
When carrying out Dimension Reduction Analysis, according to two hypothesis：Blood flow flow is proportional to pressure, is inversely proportional to resistance coefficient, k-th
The blood flow flow Q of segmentationkCalculation formula it is as follows：
Skuk=Qk (9)
By fluid governing equation (1) (2) and boundary control equations (3) can in the hope of the blood flow velocity μ of each segmentation of blood vessels,
Then every section of blood vessel can be calculated in the hope of the blood flow of this segmented vessel by formula (4)-(8) by formula (9)
Resistance Value.
The pressure drop Δ P of every section blood vessel can be finally calculated by formula (10)k, and then obtain the pressure of blood vessel everywhere
Value.
Coronary artery overall network figure is as shown in figure 4, arterial blood enters coronary artery by left ventricle through aorta, in figure,
RCA is arteria coronaria dextra, LCA is arteria coroaria sinistra, LCX is rami circumflexus arteriae coronariae sinistrae, LAD is ramus descendens anterior arteriae coronariae sinistrae,
Each number refers to the number of coronary artery difference branch.
Under different HR Heart Rates, the blood flow profile of flowrate of a cardiac cycle is as shown in figure 5, in different HR Heart Rates
Under, blood flow flow has variation, corresponding affects on the computational accuracy of FFR.
The calculating of blood flow flow uses the prior art, referring specifically to document I.E.Vignon-Clementel,
C.A.Figueroa,K.E.Jansen and C.A.Taylor,Outflow boundary conditions for three-
dimensional finite element modeling of blood flow and pressure in arteries,
Computer Methods in Applied Mechanics and Engineering,195(29):3776-3796,
2006.。
The pressure value in coronary artery everywhere is calculated according to blood flow flow and resistance coefficient, using the prior art, tool
Body is referring to document Byar D, Fiddian R V, Quereau M, et al.The fallacy of applying the
Poiseuille equation to segmental arterial stenosis[J].American heart journal,
1965,70(2):216-224.。
The blood flow reserve score of corresponding position is calculated based on the pressure value in coronary artery everywhere in step S4.
The calculation formula of blood flow reserve score FFR is as follows：
In formula：PDista writing brushesFor the pressure value of narrow far downstream end；
PaorticFor the pressure value of narrow upstream proximal end.
For hemadostewnosis model as shown in fig. 6, under normal circumstances, it is 1 that blood flow upstream and downstream pressure, which does not have significant change, i.e. FFR,
When occurring narrow in blood vessel, the pressure value of narrow far downstream end significantly reduces, and FFR is less than 1.
Embodiment 2
The present embodiment is difference from example 1 is that dimensionality reduction model building method, before building dimensionality reduction model, together
Sample blocks cholesterol plaques.
The construction method of dimensionality reduction model, including：
Step S1-2-1 pre-processes coronary artery medical image, obtains binary image, specifically includes：
In step S1-2-1, the coronary artery medical image includes multiple two dimensional gray distribution maps, according to slice sequence
Each image is arranged, following processing is done for each image：
Step S1-2-1-1 is based on the corresponding substrate image of each image creation, and each region has difference in substrate image
Gray threshold；
Step S1-2-1-2 carries out binary conversion treatment to corresponding projected image using substrate image, obtains projected image
Binary image；
Step S1-2-1-3 builds the binary picture of coronary artery medical image using the binary image of each image
Picture.
Step S1-2-2 carries out micronization processes to binary image, obtains center line vector coronarius.
Step S1-2-3 traverses coronary artery along the center line vector, using center line everywhere unit vector as transversal
The normal vector in face does cross section to coronary artery, and the boundary of coronary artery cross section is determined according to gray threshold, to cross section into
Row integral obtains the cross-sectional area of coronary artery corresponding position, according to the cross section of the center line vector sum coronary artery everywhere
Product establishes the dimensionality reduction model.
The determination process for not including bifurcation in the present embodiment, it is coronal by being obtained to binary image progress micronization processes
The center line of artery major blood vessel and branch vessel vector, the center line vector are different from embodiment 1 between two bifurcations
Vector, but (b) directly passes through the center knot that step S1-2-1, step S1-2-2 and step 1-2-3 are obtained from Fig. 2
Structure.
In addition to the building process of dimensionality reduction model, remaining step is the same as embodiment 1.
Embodiment 3
A kind of computer readable storage medium, the computer-readable recording medium storage have computer program, the meter
Calculation machine program be subsequently can by computer device execute when realize as described in embodiment 1 or embodiment 2 based on coronary artery dimensionality reduction
The method that model obtains blood flow reserve score.
Embodiment 4
It is a kind of to obtain the device of blood flow reserve score, including computer storage, computer processor and it is stored in institute
The computer program that can be executed in computer storage and on the computer processor is stated, the computer processor executes
When the computer program, realizes and blood flow is obtained based on coronary artery dimensionality reduction model as described in embodiment 1 or embodiment 2
The method for laying in score.
The present embodiment device is configurable on high in the clouds, obtains coronary artery image by the remote terminal being attached thereto, may be used also
To be that the present embodiment device is inherently configured in terminal, directly obtained medical imaging device or by way of being manually entered coronal
Artery image.
Embodiment 5
A kind of system obtaining blood flow reserve score, including terminal and server, the server include that computer is deposited
It reservoir, computer processor and is stored in the computer storage and can be executed on the computer processor
Computer program, the server obtain coronary artery medical image and coronary artery related physiological parameters from terminal；It is described
When computer processor executes the computer program, the acquisition blood flow reserve score as described in embodiment 1 or embodiment 2 is realized
Method.
According to the disclosure and teachings of the above specification, those skilled in the art in the invention can also be to above-mentioned embodiment party
Formula carries out change and modification appropriate.Therefore, the invention is not limited in specific implementation modes disclosed and described above, to this
Some modifications and changes of invention should also be as falling into the scope of the claims of the present invention.In addition, although this specification
In used some specific terms, these terms are merely for convenience of description, does not limit the present invention in any way.
Claims (9)
1. a kind of method obtaining blood flow reserve score based on coronary artery dimensionality reduction model, which is characterized in that including：
Step S1 obtains and handles coronary artery medical image, obtains the dimensionality reduction model of expression coronary artery geometry topological structure,
The dimensionality reduction model includes the cross-sectional area of center line vector sum coronary artery coronarius everywhere；
Step S2 obtains coronary artery related physiological parameters, and calculates resistance of the coronary artery to blood flow according to dimensionality reduction model
Force coefficient；
Step S3, according in coronary artery blood flow flow and the resistance coefficient, calculate blood everywhere in coronary artery
Pressure value；
The blood flow reserve score of corresponding position is calculated based on the pressure value in coronary artery everywhere in step S4.
2. the method for obtaining blood flow reserve score based on coronary artery dimensionality reduction model as described in claim 1, feature
It is, the construction method of the dimensionality reduction model, including：
Step S1-1-1 chooses entrance coronarius as initial position, initial in the coronary artery medical image
At position, the cross section of coronary artery inlet is obtained, using the geometric center of gravity of cross section as the central point of the cross section, in
Heart point determines two orthogonal feature vectors as origin, according to the intersection point of two feature vectors and coronary artery periphery,
Determine initial position cross-sectional area coronarius；
Step S1-1-2, along the direction both perpendicular to two feature vectors, with two feature vectors of pre- fixed step size synchronous translational,
According to the intersection point of two feature vectors and coronary artery periphery, the cross-sectional area of corresponding position coronary artery cross section is determined,
Using the geometric center of gravity of cross section as the central point of coronary artery cross section at this；
Step S1-1-3 determines bifurcation coronarius according to the changing value of cross-sectional area, at two bifurcations
Heart point location determination center line vector, the dimensionality reduction is established according to the cross-sectional area of the center line vector sum coronary artery everywhere
Model.
3. the method for obtaining blood flow reserve score based on coronary artery dimensionality reduction model as claimed in claim 2, feature
It is, in step S1-1-1 and step S1-1-2, coronary artery periphery is obtained using edge detection, in the side of two feature vectors
Upwards, the diameter of coronary artery periphery is respectively d2And d3, rp=(d2+d3)/4, d2And d3The center of circle overlap be point O, will be coronal
It is the center of circle with r that periarterial, which is approximately using point O,pCross-sectional area is calculated for the circle of radius.
4. the method for obtaining blood flow reserve score based on coronary artery dimensionality reduction model as claimed in claim 2, feature
It is, in step S1-1-3, if it is determined that factor g > 1.9, then be bifurcated coronarius between cross section at coronary artery two
Point, judgement factor g=max { d2, d3}/min{d2, d3}。
5. the method for obtaining blood flow reserve score based on coronary artery dimensionality reduction model as described in claim 1, feature
It is, the construction method of the dimensionality reduction model, including：
Step S1-2-1 pre-processes the coronary artery medical image, obtains binary image；
Step S1-2-2 carries out micronization processes to binary image, obtains center line vector coronarius；
Step S1-2-3 traverses coronary artery along the center line vector, using center line everywhere unit vector as cross section
Normal vector does cross section to coronary artery, and the boundary of coronary artery cross section is determined according to gray threshold, is accumulated to cross section
The cross-sectional area for getting coronary artery corresponding position is built according to the cross-sectional area of the center line vector sum coronary artery everywhere
Found the dimensionality reduction model.
6. the method for obtaining blood flow reserve score based on coronary artery dimensionality reduction model as claimed in claim 5, feature
It is, in step S1-2-1, the coronary artery medical image includes multiple two dimensional gray distribution maps, is ranked sequentially according to slice
Each image does following processing for each image：
Step S1-2-1-1 is based on the corresponding substrate image of each image creation, and each region has different ashes in substrate image
Spend threshold value；
Step S1-2-1-2 carries out binary conversion treatment to corresponding projected image using substrate image, obtains the two of projected image
Value image；
Step S1-2-1-3 builds the binary image of coronary artery medical image using the binary image of each image.
7. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, feature to exist
In the computer program, which is subsequently can by computer when device executes, realizes that claim 1~6 any one of them such as is based on coronal move
The method that arteries and veins blood vessel dimensionality reduction model obtains blood flow reserve score.
8. a kind of device obtaining blood flow reserve score, including computer storage, computer processor and it is stored in described
In computer storage and the computer program that can be executed on the computer processor, which is characterized in that the computer
When processor executes the computer program, realize that claim 1~6 any one of them such as is based on coronary artery dimensionality reduction
The method that model obtains blood flow reserve score.
9. a kind of system obtaining blood flow reserve score, including terminal and server, the server includes computer storage
Device, computer processor and it is stored in the meter that can be executed in the computer storage and on the computer processor
Calculation machine program, which is characterized in that the server obtains coronary artery medical image and coronary artery relevant physiological from terminal
Parameter；When the computer processor executes the computer program, realize that claim 1~6 any one of them such as obtains
The method of blood flow reserve score.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810516585.0A CN108735270A (en) | 2018-05-25 | 2018-05-25 | Blood flow reserve score acquisition methods, device, system and computer storage media based on dimensionality reduction model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810516585.0A CN108735270A (en) | 2018-05-25 | 2018-05-25 | Blood flow reserve score acquisition methods, device, system and computer storage media based on dimensionality reduction model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108735270A true CN108735270A (en) | 2018-11-02 |
Family
ID=63936090
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810516585.0A Pending CN108735270A (en) | 2018-05-25 | 2018-05-25 | Blood flow reserve score acquisition methods, device, system and computer storage media based on dimensionality reduction model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108735270A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110120031A (en) * | 2019-04-02 | 2019-08-13 | 四川锦江电子科技有限公司 | A kind of method and apparatus obtaining vascular flow deposit score |
| CN111134651A (en) * | 2019-12-09 | 2020-05-12 | 杭州脉流科技有限公司 | Method, device and system for calculating fractional flow reserve based on intracavity images and computer storage medium |
| CN111161342A (en) * | 2019-12-09 | 2020-05-15 | 杭州脉流科技有限公司 | Method, device, equipment and system for obtaining fractional flow reserve based on coronary angiography image and readable storage medium |
| CN111227822A (en) * | 2018-11-28 | 2020-06-05 | 苏州润心医疗器械有限公司 | Coronary artery blood flow reserve fraction calculation method based on myocardial blood flow volume and CT image |
| CN111227821A (en) * | 2018-11-28 | 2020-06-05 | 苏州润心医疗器械有限公司 | Microcirculation resistance index calculation method based on myocardial blood flow and CT (computed tomography) images |
| CN112690814A (en) * | 2020-11-06 | 2021-04-23 | 杭州阿特瑞科技有限公司 | Low-error coronary artery blood flow reserve fraction measuring method |
| WO2021087967A1 (en) * | 2019-11-04 | 2021-05-14 | 苏州润迈德医疗科技有限公司 | Method and apparatus for acquiring blood vessel assessment parameter on basis of physiological parameter, and storage medium |
| CN112971818A (en) * | 2021-01-28 | 2021-06-18 | 杭州脉流科技有限公司 | Method and device for rapidly acquiring microcirculation resistance index, computer equipment and storage medium |
| CN113995388A (en) * | 2021-12-13 | 2022-02-01 | 数坤(北京)网络科技股份有限公司 | Fractional flow reserve calculation method and device, electronic equipment and readable storage medium |
| CN116109788A (en) * | 2023-02-15 | 2023-05-12 | 张春阳 | Method for modeling and reconstructing solid piece |
| CN116128864A (en) * | 2023-02-22 | 2023-05-16 | 北京医准智能科技有限公司 | Fractional flow reserve evaluation method, fractional flow reserve evaluation device, electronic equipment and storage medium |
| CN116636826A (en) * | 2023-07-27 | 2023-08-25 | 深圳市爱保护科技有限公司 | Training method and device of blood pressure estimation model, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101836235A (en) * | 2007-08-16 | 2010-09-15 | 皇家飞利浦电子股份有限公司 | Imaging method for sampling a cross-section plane in a three-dimensional (3d) image data volume |
| CN103300820A (en) * | 2012-03-13 | 2013-09-18 | 西门子公司 | Method and system for non-invasive functional assessment of coronary artery stenosis |
| US20160283684A1 (en) * | 2014-03-28 | 2016-09-29 | Jesse Israel Kinbarovsky | System and method for providing audiovisual feedback |
| CN106651846A (en) * | 2016-12-20 | 2017-05-10 | 中南大学湘雅医院 | Method for segmenting vasa sanguinea retinae image |
| CN107133959A (en) * | 2017-06-12 | 2017-09-05 | 上海交通大学 | A kind of quick vessel borders three-dimensional dividing method and system |
| CN107427268A (en) * | 2014-11-14 | 2017-12-01 | 西门子保健有限责任公司 | Method and system for the blood flow reserve fraction based on pure geometry machine learning |
| CN107613874A (en) * | 2015-03-31 | 2018-01-19 | 新加坡科技研究局 | Method and apparatus for assessing hemadostewnosis |
-
2018
- 2018-05-25 CN CN201810516585.0A patent/CN108735270A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101836235A (en) * | 2007-08-16 | 2010-09-15 | 皇家飞利浦电子股份有限公司 | Imaging method for sampling a cross-section plane in a three-dimensional (3d) image data volume |
| CN103300820A (en) * | 2012-03-13 | 2013-09-18 | 西门子公司 | Method and system for non-invasive functional assessment of coronary artery stenosis |
| US20160283684A1 (en) * | 2014-03-28 | 2016-09-29 | Jesse Israel Kinbarovsky | System and method for providing audiovisual feedback |
| CN107427268A (en) * | 2014-11-14 | 2017-12-01 | 西门子保健有限责任公司 | Method and system for the blood flow reserve fraction based on pure geometry machine learning |
| CN107613874A (en) * | 2015-03-31 | 2018-01-19 | 新加坡科技研究局 | Method and apparatus for assessing hemadostewnosis |
| CN106651846A (en) * | 2016-12-20 | 2017-05-10 | 中南大学湘雅医院 | Method for segmenting vasa sanguinea retinae image |
| CN107133959A (en) * | 2017-06-12 | 2017-09-05 | 上海交通大学 | A kind of quick vessel borders three-dimensional dividing method and system |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111227822A (en) * | 2018-11-28 | 2020-06-05 | 苏州润心医疗器械有限公司 | Coronary artery blood flow reserve fraction calculation method based on myocardial blood flow volume and CT image |
| CN111227821A (en) * | 2018-11-28 | 2020-06-05 | 苏州润心医疗器械有限公司 | Microcirculation resistance index calculation method based on myocardial blood flow and CT (computed tomography) images |
| CN111227822B (en) * | 2018-11-28 | 2022-02-11 | 苏州润迈德医疗科技有限公司 | Coronary artery blood flow reserve fraction calculation method based on myocardial blood flow volume and CT image |
| CN111227821B (en) * | 2018-11-28 | 2022-02-11 | 苏州润迈德医疗科技有限公司 | Microcirculation resistance index calculation method based on myocardial blood flow and CT (computed tomography) images |
| CN110120031A (en) * | 2019-04-02 | 2019-08-13 | 四川锦江电子科技有限公司 | A kind of method and apparatus obtaining vascular flow deposit score |
| CN110120031B (en) * | 2019-04-02 | 2022-05-31 | 四川锦江电子科技有限公司 | Method and device for obtaining blood flow reserve fraction of blood vessel |
| WO2021087967A1 (en) * | 2019-11-04 | 2021-05-14 | 苏州润迈德医疗科技有限公司 | Method and apparatus for acquiring blood vessel assessment parameter on basis of physiological parameter, and storage medium |
| CN111134651B (en) * | 2019-12-09 | 2022-03-08 | 杭州脉流科技有限公司 | Method, device and system for calculating fractional flow reserve based on intracavity images and computer storage medium |
| CN111134651A (en) * | 2019-12-09 | 2020-05-12 | 杭州脉流科技有限公司 | Method, device and system for calculating fractional flow reserve based on intracavity images and computer storage medium |
| CN111161342A (en) * | 2019-12-09 | 2020-05-15 | 杭州脉流科技有限公司 | Method, device, equipment and system for obtaining fractional flow reserve based on coronary angiography image and readable storage medium |
| CN111161342B (en) * | 2019-12-09 | 2023-08-29 | 杭州脉流科技有限公司 | Method, apparatus, device, system and readable storage medium for obtaining fractional flow reserve based on coronary angiography image |
| CN112690814A (en) * | 2020-11-06 | 2021-04-23 | 杭州阿特瑞科技有限公司 | Low-error coronary artery blood flow reserve fraction measuring method |
| CN112971818B (en) * | 2021-01-28 | 2022-10-04 | 杭州脉流科技有限公司 | Method and device for acquiring microcirculation resistance index, computer equipment and storage medium |
| CN112971818A (en) * | 2021-01-28 | 2021-06-18 | 杭州脉流科技有限公司 | Method and device for rapidly acquiring microcirculation resistance index, computer equipment and storage medium |
| CN113995388A (en) * | 2021-12-13 | 2022-02-01 | 数坤(北京)网络科技股份有限公司 | Fractional flow reserve calculation method and device, electronic equipment and readable storage medium |
| CN116109788A (en) * | 2023-02-15 | 2023-05-12 | 张春阳 | Method for modeling and reconstructing solid piece |
| CN116109788B (en) * | 2023-02-15 | 2023-07-04 | 张春阳 | Method for modeling and reconstructing solid piece |
| CN116128864A (en) * | 2023-02-22 | 2023-05-16 | 北京医准智能科技有限公司 | Fractional flow reserve evaluation method, fractional flow reserve evaluation device, electronic equipment and storage medium |
| CN116128864B (en) * | 2023-02-22 | 2024-04-23 | 浙江医准智能科技有限公司 | Fractional flow reserve evaluation method, fractional flow reserve evaluation device, electronic equipment and storage medium |
| CN116636826A (en) * | 2023-07-27 | 2023-08-25 | 深圳市爱保护科技有限公司 | Training method and device of blood pressure estimation model, electronic equipment and storage medium |
| CN116636826B (en) * | 2023-07-27 | 2023-09-22 | 深圳市爱保护科技有限公司 | Training method and device of blood pressure estimation model, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108735270A (en) | Blood flow reserve score acquisition methods, device, system and computer storage media based on dimensionality reduction model | |
| US11583340B2 (en) | Method and system for image processing to determine blood flow | |
| US20220406470A1 (en) | Systems and methods for processing electronic images to determine flow using flow ratio | |
| AU2017200000B2 (en) | Method and system for modeling blood flow with boundary conditions for optimized diagnostic performance | |
| EP3140757B1 (en) | Method and system for non-invasive functional assessment of coronary artery stenosis using flow computations in models based on diseased patients and hypothetical normal anatomical models | |
| CN110853029A (en) | Method, system, and medium for automatically predicting blood flow characteristics based on medical images | |
| CN114664455A (en) | Coronary artery blood flow reserve fraction calculation method and device | |
| WO2022136688A1 (en) | Non-invasive method for determining a vessel damage indicator |
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 |