CN117556726A - Microcirculation resistance index calculating method, device, equipment and storage medium - Google Patents
Microcirculation resistance index calculating method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117556726A CN117556726A CN202311445557.1A CN202311445557A CN117556726A CN 117556726 A CN117556726 A CN 117556726A CN 202311445557 A CN202311445557 A CN 202311445557A CN 117556726 A CN117556726 A CN 117556726A
- Authority
- CN
- China
- Prior art keywords
- coronary
- coronary artery
- pressure drop
- resistance index
- dimensional
- 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
- 230000004089 microcirculation Effects 0.000 title claims abstract description 100
- 238000000034 method Methods 0.000 title claims abstract description 60
- 210000004351 coronary vessel Anatomy 0.000 claims abstract description 223
- 239000002872 contrast media Substances 0.000 claims abstract description 50
- 238000004364 calculation method Methods 0.000 claims abstract description 33
- 238000013135 deep learning Methods 0.000 claims abstract description 17
- 230000009466 transformation Effects 0.000 claims abstract description 16
- 238000012549 training Methods 0.000 claims abstract description 11
- 238000002586 coronary angiography Methods 0.000 claims description 17
- 230000009467 reduction Effects 0.000 claims description 15
- 238000005070 sampling Methods 0.000 claims description 10
- 210000004204 blood vessel Anatomy 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 6
- 238000003709 image segmentation Methods 0.000 claims description 5
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000004088 simulation Methods 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 239000012530 fluid Substances 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000002457 bidirectional effect Effects 0.000 description 2
- 230000017531 blood circulation Effects 0.000 description 2
- 208000019484 coronary microvascular disease Diseases 0.000 description 2
- 238000013136 deep learning model Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000000004 hemodynamic effect Effects 0.000 description 2
- 238000011144 upstream manufacturing Methods 0.000 description 2
- 208000031481 Pathologic Constriction Diseases 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 201000005973 campomelic dysplasia Diseases 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000004087 circulation Effects 0.000 description 1
- 201000006815 congenital muscular dystrophy Diseases 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 208000029078 coronary artery disease Diseases 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000002526 effect on cardiovascular system Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 235000015097 nutrients Nutrition 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 238000002601 radiography Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 208000037804 stenosis Diseases 0.000 description 1
- 230000036262 stenosis Effects 0.000 description 1
- 230000002792 vascular Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
- G06N3/0455—Auto-encoder networks; Encoder-decoder networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10116—X-ray image
- G06T2207/10121—Fluoroscopy
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
- G06T2207/30104—Vascular flow; Blood flow; Perfusion
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Computing Systems (AREA)
- Computer Hardware Design (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Mathematical Optimization (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Analysis (AREA)
- Fluid Mechanics (AREA)
- Medical Informatics (AREA)
- Algebra (AREA)
- Health & Medical Sciences (AREA)
- Pure & Applied Mathematics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computer Graphics (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
Abstract
The invention belongs to the technical field of microcirculation and discloses a microcirculation resistance index calculation method, a device, equipment and a storage medium. The method comprises the following steps: performing contour transformation on a coronary three-dimensional model of a coronary artery to obtain a plurality of three-dimensional contour lines of the coronary artery; carrying out outlet information prediction according to a plurality of three-dimensional contour lines, coronary boundary information of the coronary arteries and a target pressure drop prediction model, so as to obtain predicted outlet pressure drop of the coronary arteries, wherein the target pressure drop prediction model is obtained by training a deep learning network based on a sample coronary artery set; determining a microcirculation resistance index of the coronary artery according to the predicted outlet pressure drop and the contrast agent flowing time. Through the mode, the efficiency and the accuracy of the microcirculation resistance index calculation are improved, meanwhile, the adaptability is high, the method can be widely applied to terminal equipment, and the requirements on the terminal equipment and operators are reduced.
Description
Technical Field
The present invention relates to the field of microcirculation technologies, and in particular, to a method, an apparatus, a device, and a storage medium for calculating a microcirculation resistance index.
Background
Microcirculation, which is the smallest blood vessel in the heart responsible for the delivery of oxygen and nutrients to the heart, is indicated by the microcirculation resistance index (Index of Microcirculatory Resistance, IMR) which can be used as an index for the clinical assessment of microcirculation disorders (coronary microvascular disease, CMD). The IMR has the advantages of quantitatively evaluating the microcirculation resistance, having good repeatability of measurement results, being independent of hemodynamic changes and the like. Recent researches show that the IMR has good effects on diagnosis of microcirculation disturbance, prediction of occurrence rate of long-term cardiovascular adverse events of patients with coronary heart disease and the like. Traditional IMR measurement methods require invasive measurements, which require insertion of a catheter into the coronary artery, and measurement of the coronary artery tip pressure by a sensor on the catheter. The method has high accuracy, but the invasive operation has high cost, high risk and high requirement on operators, so that the clinical application of the method is limited. In recent years, a method for non-invasively evaluating IMR by Computational Fluid Dynamics (CFD) simulation after reconstructing a three-dimensional model by using a coronary angiography image is rapidly developed, and compared with invasive measurement, the method for simulatively computing IMR has lower cost and less risk to a patient, but CFD simulation requires high-performance computers such as supercomputers and servers, and the calculation takes a long time.
Disclosure of Invention
The invention mainly aims to provide a microcirculation resistance index calculating method, a device, equipment and a storage medium, which aim to solve the technical problem of how to reduce the calculating cost while improving the calculating efficiency of the microcirculation resistance index in the prior art.
In order to achieve the above object, the present invention provides a microcirculation resistance index calculating method including:
performing contour transformation on a coronary three-dimensional model of a coronary artery to obtain a plurality of three-dimensional contour lines of the coronary artery;
carrying out outlet information prediction according to a plurality of three-dimensional contour lines, coronary boundary information of the coronary arteries and a target pressure drop prediction model, so as to obtain predicted outlet pressure drop of the coronary arteries, wherein the target pressure drop prediction model is obtained by training a deep learning network based on a sample coronary artery set;
determining a microcirculation resistance index of the coronary artery according to the predicted outlet pressure drop and the contrast agent flowing time.
Optionally, the predicting the outlet information according to the three-dimensional contour lines, the coronary boundary information of the coronary artery and the target pressure drop prediction model to obtain a predicted outlet pressure drop of the coronary artery includes:
determining a plurality of three-dimensional point coordinates on each three-dimensional contour line according to the plurality of three-dimensional contour lines;
performing feature dimension reduction on a plurality of three-dimensional point coordinates on each three-dimensional contour line according to an encoder network to obtain first coordinate features on each three-dimensional contour line;
and inputting the first coordinate characteristics of each three-dimensional contour line, the coronary artery boundary information of the coronary artery and the position relation of each three-dimensional contour line to a target pressure drop prediction model, and predicting outlet information according to the first coordinate characteristics of each three-dimensional contour line, the boundary information and the position relation of each three-dimensional contour line by using the target pressure drop prediction model to obtain the predicted outlet pressure drop of the coronary artery.
Optionally, the predicting the outlet information according to the three-dimensional contour lines, the coronary boundary information of the coronary artery and the target pressure drop prediction model to obtain a predicted outlet pressure drop of the coronary artery includes:
dividing the coronary three-dimensional model to obtain a plurality of coronary segmented models of the coronary artery;
determining an interface contour line of each coronary artery segmentation model in a plurality of three-dimensional contour lines of the coronary arteries;
performing feature dimension reduction on a plurality of three-dimensional point coordinates on each interface contour line according to the encoder network to obtain second coordinate features of each interface contour line;
and inputting second coordinate characteristics of each interface contour line, coronary artery boundary information of the coronary artery and the position relation of each interface contour line to a target pressure drop prediction model, and predicting outlet information according to the second coordinate characteristics of each interface contour line, the boundary information and the position relation of each interface contour line through the target pressure drop prediction model to obtain predicted outlet pressure drop of the coronary artery.
Optionally, the predicting the outlet information according to the three-dimensional contour lines, the coronary boundary information of the coronary artery and the target pressure drop prediction model to obtain a predicted outlet pressure drop of the coronary artery, before the predicting, further includes:
acquiring the blood vessel type of the coronary artery;
determining an inlet pressure, an inlet velocity and an inlet flow from the vessel type;
and determining coronary boundary information of the coronary artery according to the inlet pressure, the inlet speed and the inlet flow.
Optionally, before performing contour transformation on the coronary three-dimensional model of the coronary artery to obtain a plurality of three-dimensional contour lines of the coronary artery, the method further includes:
acquiring a coronary angiography image sequence of a coronary artery;
image segmentation is carried out on the coronary angiography image sequence to obtain coronary vessel images with a plurality of angles;
and performing image alignment on the coronary vessel images at a plurality of angles to generate a coronary three-dimensional model of the coronary artery.
Optionally, before determining the microcirculation resistance index of the coronary artery according to the predicted outlet pressure drop and the contrast agent flowing time, the method further comprises:
determining a contrast agent image quantity from a coronary angiography image sequence of the coronary arteries;
acquiring a preset sampling frame rate;
and performing time calculation according to the number of the contrast agent images and the preset sampling frame rate, and determining the flowing time of the contrast agent.
Optionally, the determining the microcirculation resistance index of the coronary artery according to the predicted outlet pressure drop and contrast agent flow time comprises:
acquiring aortic root pressure;
performing index calculation according to the aortic root pressure, the predicted outlet pressure drop and the contrast agent flowing time, and determining a microcirculation resistance index of the coronary artery;
after determining the microcirculation resistance index of the coronary artery according to the predicted outlet pressure drop and the contrast agent flowing time, the method further comprises:
when the microcirculation resistance index exceeds a target index range, generating alarm information according to the microcirculation resistance index;
and sending the alarm information to the user terminal for alarm.
In addition, in order to achieve the above object, the present invention also proposes a microcirculation resistance index computing device including:
the transformation module is used for carrying out contour transformation on the coronary three-dimensional model of the coronary artery to obtain a plurality of three-dimensional contour lines of the coronary artery;
the prediction module is used for predicting outlet information according to a plurality of three-dimensional contour lines, coronary boundary information of the coronary arteries and a target pressure drop prediction model, so as to obtain predicted outlet pressure drop of the coronary arteries, wherein the target pressure drop prediction model is obtained by training a deep learning network based on a sample coronary artery set;
a processing module for determining a microcirculation resistance index of the coronary artery based on the predicted outlet pressure drop and contrast agent flow-through time.
In addition, in order to achieve the above object, the present invention also proposes a microcirculation resistance index computing device including: a memory, a processor, and a microcirculation resistance index calculation program stored on the memory and executable on the processor, the microcirculation resistance index calculation program configured to implement the microcirculation resistance index calculation method as described above.
In addition, in order to achieve the above object, the present invention also proposes a storage medium having stored thereon a microcirculation resistance index calculation program which, when executed by a processor, implements the microcirculation resistance index calculation method as described above.
The method comprises the steps of obtaining a plurality of three-dimensional contour lines of a coronary artery by carrying out contour transformation on a coronary artery three-dimensional model of the coronary artery; carrying out outlet information prediction according to a plurality of three-dimensional contour lines, coronary boundary information of the coronary arteries and a target pressure drop prediction model, so as to obtain predicted outlet pressure drop of the coronary arteries, wherein the target pressure drop prediction model is obtained by training a deep learning network based on a sample coronary artery set; determining a microcirculation resistance index of the coronary artery according to the predicted outlet pressure drop and the contrast agent flowing time. By means of the method, the outlet information is predicted according to the three-dimensional contour lines of the coronary artery, the coronary artery boundary information and the target pressure drop prediction model, the predicted outlet pressure drop of the coronary artery is obtained, the microcirculation resistance index of the coronary artery is determined based on the predicted outlet pressure drop and the contrast agent flowing time, the efficiency and the accuracy of calculation of the microcirculation resistance index are improved, meanwhile, the method is high in applicability and can be widely applied to terminal equipment, requirements on the terminal equipment and operators are reduced, and meanwhile, the calculation cost is reduced.
Drawings
FIG. 1 is a schematic diagram of a micro-circulation resistance index calculation device of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flowchart of a first embodiment of a method for calculating a microcirculatory resistance index according to the invention;
FIG. 3 is a flowchart of a second embodiment of the method for calculating the microcirculatory resistance index according to the invention;
FIG. 4 is a schematic diagram of a prediction flow chart of an embodiment of a method for calculating a microcirculatory resistance index according to the invention;
FIG. 5 is a schematic diagram illustrating a method for calculating a microcirculatory resistance index according to an embodiment of the invention;
FIG. 6 is a schematic diagram of a prediction flow chart of an embodiment of a method for calculating a microcirculatory resistance index according to the invention;
FIG. 7 is a schematic diagram of a prediction flow chart of an embodiment of a method for calculating a microcirculatory resistance index according to the invention;
fig. 8 is a block diagram showing the construction of a first embodiment of the apparatus for calculating a microcirculatory resistance index according to the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a micro-circulation resistance index calculating device of a hardware running environment according to an embodiment of the present invention.
As shown in fig. 1, the microcirculation resistance index calculating device may include: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) Memory or a stable nonvolatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
Those skilled in the art will appreciate that the structure shown in fig. 1 is not limiting of the microcirculation resistance index computing device and may include more or fewer components than shown, or certain components may be combined, or a different arrangement of components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and a microcirculation resistance index calculation program may be included in the memory 1005 as one storage medium.
In the microcirculatory resistance index computing device shown in fig. 1, the network interface 1004 is primarily used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the microcirculation resistance index calculation device of the present invention may be disposed in the microcirculation resistance index calculation device, and the microcirculation resistance index calculation device invokes the microcirculation resistance index calculation program stored in the memory 1005 through the processor 1001, and executes the microcirculation resistance index calculation method provided by the embodiment of the present invention.
An embodiment of the present invention provides a method for calculating a microcirculatory resistance index, and referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of a microcirculatory resistance index calculation method according to the present invention.
The microcirculation resistance index calculating method comprises the following steps:
step S10: and performing contour transformation on the coronary three-dimensional model of the coronary artery to obtain a plurality of three-dimensional contour lines of the coronary artery.
It should be noted that, the execution body of the embodiment is a micro-circulation resistance index computing device, where the micro-circulation resistance index computing device has functions of data processing, data communication, program running, and the like, and the micro-circulation resistance index computing device may be an integrated controller, a control computer, or other devices with similar functions, which is not limited in this embodiment.
It is understood that the three-dimensional model of coronary artery refers to a three-dimensional vascular model of coronary artery, which is constructed based on a coronary angiography image of the coronary artery. And obtaining a coronary three-dimensional model of the coronary artery of which the microcirculation resistance index is required to be calculated, and converting the coronary three-dimensional model into contour lines of one circle by one circle, thereby obtaining a plurality of three-dimensional contour lines of the coronary artery.
In a specific implementation, in order to obtain an accurate coronary three-dimensional model, before performing contour transformation on the coronary three-dimensional model of the coronary artery to obtain a plurality of three-dimensional contour lines of the coronary artery, the method further includes: acquiring a coronary angiography image sequence of a coronary artery; image segmentation is carried out on the coronary angiography image sequence to obtain coronary vessel images with a plurality of angles; and performing image alignment on the coronary vessel images at a plurality of angles to generate a coronary three-dimensional model of the coronary artery.
The coronary angiography image sequence of the coronary artery is obtained, two-dimensional image segmentation is carried out on the coronary angiography image sequence by using a machine learning or deep learning method, images of the coronary arteries under two different angles are obtained, the images of the coronary arteries under the two different angles are coronary vessel images under a plurality of angles, the coronary vessel images under the plurality of angles are aligned in an image mode, and a coronary three-dimensional model of the coronary artery is generated by splicing.
Step S20: and predicting outlet information according to the three-dimensional contour lines, coronary boundary information of the coronary arteries and a target pressure drop prediction model, so as to obtain predicted outlet pressure drop of the coronary arteries, wherein the target pressure drop prediction model is obtained by training a deep learning network based on a sample coronary artery set.
It should be noted that, a plurality of three-dimensional contour lines of the coronary artery and coronary artery boundary information of the coronary artery are input to a target pressure drop prediction model, the plurality of three-dimensional contour lines are used as input of deep learning, the coronary artery boundary information is used as input of a hidden layer, the target pressure drop prediction model predicts the pressure drop on each contour respectively, and finally, the predicted pressure drop at the outlet of the coronary artery is output, and the predicted pressure drop at the outlet of the coronary artery is the predicted outlet pressure drop dP.
It can be understood that the target pressure drop prediction model is fluid simulation data of a large number of blood vessel models obtained through computational fluid mechanics simulation, the data is used as a sample coronary artery set, a deep learning model capable of rapidly predicting the pressure value in the blood vessel is trained by applying a deep learning method, in this embodiment, the deep learning network can be a multi-layer fully-connected network, a circulating neural network, a convolutional neural network or the like, and this embodiment is not limited thereto.
In a specific implementation, the coronary boundary information refers to a preset boundary condition of a coronary artery, and in order to obtain accurate coronary boundary information, further, the predicting outlet information according to the multiple three-dimensional contour lines, the coronary boundary information of the coronary artery and a target pressure drop prediction model, to obtain a predicted outlet pressure drop of the coronary artery, includes: acquiring the blood vessel type of the coronary artery; determining an inlet pressure, an inlet velocity and an inlet flow from the vessel type; and determining coronary boundary information of the coronary artery according to the inlet pressure, the inlet speed and the inlet flow.
Since the coronary artery may be the left coronary artery, the right coronary artery, or other blood vessels, the vessel type of the coronary artery is acquired, and the inlet pressure, the inlet flow, and the inlet velocity of the coronary artery are acquired according to the vessel type, and all of the above parameters are parameters set according to the vessel type, and the inlet pressure, the inlet flow, and the inlet velocity of the coronary artery are used as boundary conditions of the coronary artery.
Step S30: determining a microcirculation resistance index of the coronary artery according to the predicted outlet pressure drop and the contrast agent flowing time.
The contrast agent flow time refers to the average transit time Tmn of the contrast agent flowing from the coronary three-dimensional model inlet to the model outlet of the coronary artery, and the microcirculation resistance index of the coronary artery can be determined according to the predicted outlet pressure drop and the contrast agent flow time.
It will be appreciated that, in order to obtain an accurate contrast agent flow time, before determining the microcirculation resistance index of the coronary artery according to the predicted outlet pressure drop and the contrast agent flow time, the method further includes: determining a contrast agent image quantity from a coronary angiography image sequence of the coronary arteries; acquiring a preset sampling frame rate; and performing time calculation according to the number of the contrast agent images and the preset sampling frame rate, and determining the flowing time of the contrast agent.
In specific implementation, determining the number of images required by the contrast agent flowing in the coronary artery for a certain length according to the coronary angiography image sequence, wherein the number of images required by the contrast agent flowing in the coronary artery for a certain length is the number of contrast agent images, acquiring a preset contrast sampling frame rate, dividing the number of contrast agent images by the preset sampling frame rate, and obtaining a result which is the flowing time of the contrast agent.
In order to accurately calculate the microcirculation resistance index based on the predicted outlet pressure drop and the contrast agent flowing time, the determining the microcirculation resistance index of the coronary artery according to the predicted outlet pressure drop and the contrast agent flowing time further includes: acquiring aortic root pressure; performing index calculation according to the aortic root pressure, the predicted outlet pressure drop and the contrast agent flowing time, and determining a microcirculation resistance index of the coronary artery; after determining the microcirculation resistance index of the coronary artery according to the predicted outlet pressure drop and the contrast agent flowing time, the method further comprises: when the microcirculation resistance index exceeds a target index range, generating alarm information according to the microcirculation resistance index; and sending the alarm information to the user terminal for alarm.
It will be appreciated that aortic root pressure P a Measured with pressure guide wire during radiography, according to aortic root pressure P a Exponential calculation of the predicted exit pressure drop dP and the contrast agent flow time Tmn to determine the microcirculation resistance index imr= (P) of the coronary artery a -dP)Tmn。
In a specific implementation, when the microcirculation resistance index exceeds the target index range, it is indicated that the microcirculation resistance index of the coronary artery is not in the normal index range, and at this time, alarm information is generated according to the microcirculation resistance index and sent to the user terminal for alarm.
In the embodiment, a plurality of three-dimensional contour lines of the coronary artery are obtained by carrying out contour transformation on a coronary artery three-dimensional model of the coronary artery; carrying out outlet information prediction according to a plurality of three-dimensional contour lines, coronary boundary information of the coronary arteries and a target pressure drop prediction model, so as to obtain predicted outlet pressure drop of the coronary arteries, wherein the target pressure drop prediction model is obtained by training a deep learning network based on a sample coronary artery set; determining a microcirculation resistance index of the coronary artery according to the predicted outlet pressure drop and the contrast agent flowing time. By means of the method, the outlet information is predicted according to the three-dimensional contour lines of the coronary artery, the coronary artery boundary information and the target pressure drop prediction model, the predicted outlet pressure drop of the coronary artery is obtained, the microcirculation resistance index of the coronary artery is determined based on the predicted outlet pressure drop and the contrast agent flowing time, the efficiency and the accuracy of calculation of the microcirculation resistance index are improved, meanwhile, the method is high in applicability and can be widely applied to terminal equipment, requirements on the terminal equipment and operators are reduced, and meanwhile, the calculation cost is reduced.
Referring to fig. 3, fig. 3 is a flowchart of a second embodiment of a method for calculating a microcirculatory resistance index according to the invention.
Based on the first embodiment, the step S20 in the method for calculating a microcirculatory resistance index according to the present embodiment includes:
step S21: and determining a plurality of three-dimensional point coordinates on each three-dimensional contour line according to the plurality of three-dimensional contour lines.
It should be noted that the same number of three-dimensional point coordinates are taken on each three-dimensional contour line.
Step S22: and carrying out feature dimension reduction on the coordinates of the plurality of three-dimensional points on each three-dimensional contour line according to the encoder network to obtain a first coordinate feature on each three-dimensional contour line.
In order to increase the training speed and the later prediction speed of the deep learning model, the feature dimension reduction encoder network may first perform feature dimension reduction on a plurality of three-dimensional point coordinates on each input three-dimensional contour line, reduce the feature with fewer variables, and the dimension reduced three-dimensional point coordinates are the first coordinate features.
Step S23: and inputting the first coordinate characteristics of each three-dimensional contour line, the coronary artery boundary information of the coronary artery and the position relation of each three-dimensional contour line to a target pressure drop prediction model, and predicting outlet information according to the first coordinate characteristics of each three-dimensional contour line, the boundary information and the position relation of each three-dimensional contour line by using the target pressure drop prediction model to obtain the predicted outlet pressure drop of the coronary artery.
The first coordinate feature of each three-dimensional contour line, coronary artery boundary information of the coronary artery and the position relation of each three-dimensional contour line are input into an artificial neural network in a target pressure drop prediction model, the target pressure drop prediction model predicts the pressure drop of each position in sequence, and finally the predicted outlet pressure drop of the coronary artery is output.
It can be understood that, as shown in fig. 4 and fig. 5, the coronary boundary information and the first coordinate feature of the three-dimensional contour line corresponding to the position 1 are output to the artificial neural network, the variables such as the pressure drop, the speed and the flow of the position 1 are output through the calculation of the target pressure drop prediction model, and the variables such as the pressure drop, the speed and the flow of the position 2 are output, and the variables such as the pressure drop, the speed and the flow of the position 2 can be output when the first coordinate feature of the three-dimensional contour line corresponding to the position 1 is input to the next artificial neural network, and the predicted outlet pressure drop can be obtained through such circulation.
In a specific implementation, if the dimension reduction is performed without using an encoder network, as shown in fig. 6, the coronary boundary information, the coordinates of the multiple three-dimensional points on each three-dimensional contour line, and the positional relationship of each three-dimensional contour line are directly input into the target pressure drop prediction model, so as to obtain the predicted outlet pressure drop.
It should be noted that, besides extracting the same number of three-dimensional coordinate points on each three-dimensional contour line, the coordinate feature may be obtained in a segmented manner, and further, the predicting the outlet information according to the plurality of three-dimensional contour lines, the coronary boundary information of the coronary artery and the target pressure drop prediction model to obtain the predicted outlet pressure drop of the coronary artery includes: dividing the coronary three-dimensional model to obtain a plurality of coronary segmented models of the coronary artery; determining an interface contour line of each coronary artery segmentation model in a plurality of three-dimensional contour lines of the coronary arteries; performing feature dimension reduction on a plurality of three-dimensional point coordinates on each interface contour line according to the encoder network to obtain second coordinate features of each interface contour line; and inputting second coordinate characteristics of each interface contour line, coronary artery boundary information of the coronary artery and the position relation of each interface contour line to a target pressure drop prediction model, and predicting outlet information according to the second coordinate characteristics of each interface contour line, the boundary information and the position relation of each interface contour line through the target pressure drop prediction model to obtain predicted outlet pressure drop of the coronary artery.
It can be understood that the coronary three-dimensional model is uniformly divided, the coronary three-dimensional model of the coronary artery is divided into a plurality of vessel segments, so that a plurality of coronary segmented models are obtained, the outlet contour line and the inlet contour line of each coronary segmented model are determined, the outlet contour line and the inlet contour line of each coronary segmented model are the interface contour line of each coronary segmented model, the encoder network is utilized to perform characteristic dimension reduction on a plurality of three-dimensional point coordinates on the interface contour line of each coronary segmented model, the dimension-reduced three-dimensional point coordinates are the second coordinate characteristics, and the second coordinate characteristics of each interface contour line, coronary boundary information of the coronary artery and the position relation of each interface contour line are input to the target pressure drop prediction model, so that the target pressure drop prediction model outputs predicted outlet pressure drop. In this embodiment, the coordinates of a plurality of three-dimensional points on the interface contour lines of each coronary artery segment model, coronary artery boundary information of the coronary artery, and the positional relationship of each interface contour line may also be directly input to the target pressure drop prediction model without dimension reduction.
In particular, in this embodiment, in addition to the above-described prediction methods, a bidirectional deep learning network may be used, as shown in fig. 7, because downstream hemodynamic characteristics of a blood vessel affect upstream blood flow, such as downstream stenosis may result in a decrease in blood flow of the entire blood vessel. Therefore, by utilizing a bidirectional deep learning network, downstream flow changes can be transmitted back to the upstream, so that the whole model accords with the physical rule better.
It should be noted that, by applying the deep learning method, the calculation amount of the learning model is reduced, the result can be obtained quickly only by using conventional terminal equipment, and a supercomputer or a high-performance server required by three-dimensional CFD simulation is not required, and the calculation time is 1-2 orders of magnitude less than that of the three-dimensional CFD simulation.
In the embodiment, a plurality of three-dimensional point coordinates on each three-dimensional contour line are determined according to the plurality of three-dimensional contour lines; performing feature dimension reduction on a plurality of three-dimensional point coordinates on each three-dimensional contour line according to an encoder network to obtain first coordinate features on each three-dimensional contour line; and inputting the first coordinate characteristics of each three-dimensional contour line, the coronary artery boundary information of the coronary artery and the position relation of each three-dimensional contour line to a target pressure drop prediction model, and predicting outlet information according to the first coordinate characteristics of each three-dimensional contour line, the boundary information and the position relation of each three-dimensional contour line by using the target pressure drop prediction model to obtain the predicted outlet pressure drop of the coronary artery. Through the mode, the encoder network is utilized to conduct feature dimension reduction on the three-dimensional point coordinates on each three-dimensional contour line, the first coordinate feature of each three-dimensional contour line, coronary artery boundary information of the coronary artery and the position relation of each three-dimensional contour line are input to the target pressure drop prediction model, so that the predicted outlet pressure drop of the coronary artery is obtained, and the prediction efficiency and the prediction accuracy are improved.
In addition, referring to fig. 8, an embodiment of the present invention further proposes a micro-circulation resistance index calculation device, including:
the transformation module 10 is configured to perform contour transformation on the coronary three-dimensional model of the coronary artery, so as to obtain a plurality of three-dimensional contour lines of the coronary artery.
The prediction module 20 is configured to predict outlet information according to a plurality of three-dimensional contour lines, coronary boundary information of the coronary arteries, and a target pressure drop prediction model, so as to obtain a predicted outlet pressure drop of the coronary arteries, where the target pressure drop prediction model is obtained by training a deep learning network based on a sample coronary artery set.
A processing module 30 for determining a microcirculation resistance index of the coronary artery based on the predicted outlet pressure drop and contrast agent flow-through time.
In the embodiment, a plurality of three-dimensional contour lines of the coronary artery are obtained by carrying out contour transformation on a coronary artery three-dimensional model of the coronary artery; carrying out outlet information prediction according to a plurality of three-dimensional contour lines, coronary boundary information of the coronary arteries and a target pressure drop prediction model, so as to obtain predicted outlet pressure drop of the coronary arteries, wherein the target pressure drop prediction model is obtained by training a deep learning network based on a sample coronary artery set; determining a microcirculation resistance index of the coronary artery according to the predicted outlet pressure drop and the contrast agent flowing time. By means of the method, the outlet information is predicted according to the three-dimensional contour lines of the coronary artery, the coronary artery boundary information and the target pressure drop prediction model, the predicted outlet pressure drop of the coronary artery is obtained, the microcirculation resistance index of the coronary artery is determined based on the predicted outlet pressure drop and the contrast agent flowing time, the efficiency and the accuracy of calculation of the microcirculation resistance index are improved, meanwhile, the method is high in applicability and can be widely applied to terminal equipment, requirements on the terminal equipment and operators are reduced, and meanwhile, the calculation cost is reduced.
In one embodiment, the prediction module 20 is further configured to determine a plurality of three-dimensional coordinates of points on each three-dimensional contour line according to the plurality of three-dimensional contour lines;
performing feature dimension reduction on a plurality of three-dimensional point coordinates on each three-dimensional contour line according to an encoder network to obtain first coordinate features on each three-dimensional contour line;
and inputting the first coordinate characteristics of each three-dimensional contour line, the coronary artery boundary information of the coronary artery and the position relation of each three-dimensional contour line to a target pressure drop prediction model, and predicting outlet information according to the first coordinate characteristics of each three-dimensional contour line, the boundary information and the position relation of each three-dimensional contour line by using the target pressure drop prediction model to obtain the predicted outlet pressure drop of the coronary artery.
In an embodiment, the prediction module 20 is further configured to divide the three-dimensional coronary model to obtain a plurality of coronary segmented models of the coronary arteries;
determining an interface contour line of each coronary artery segmentation model in a plurality of three-dimensional contour lines of the coronary arteries;
performing feature dimension reduction on a plurality of three-dimensional point coordinates on each interface contour line according to the encoder network to obtain second coordinate features of each interface contour line;
and inputting second coordinate characteristics of each interface contour line, coronary artery boundary information of the coronary artery and the position relation of each interface contour line to a target pressure drop prediction model, and predicting outlet information according to the second coordinate characteristics of each interface contour line, the boundary information and the position relation of each interface contour line through the target pressure drop prediction model to obtain predicted outlet pressure drop of the coronary artery.
In an embodiment, the prediction module 20 is further configured to obtain a vessel type of the coronary artery;
determining an inlet pressure, an inlet velocity and an inlet flow from the vessel type;
and determining coronary boundary information of the coronary artery according to the inlet pressure, the inlet speed and the inlet flow.
In an embodiment, the conversion module 10 is further configured to acquire a coronary angiography image sequence of the coronary arteries;
image segmentation is carried out on the coronary angiography image sequence to obtain coronary vessel images with a plurality of angles;
and performing image alignment on the coronary vessel images at a plurality of angles to generate a coronary three-dimensional model of the coronary artery.
In an embodiment, the determining module 30 is further configured to determine a number of contrast agent images from a sequence of coronary angiography images of the coronary artery;
acquiring a preset sampling frame rate;
and performing time calculation according to the number of the contrast agent images and the preset sampling frame rate, and determining the flowing time of the contrast agent.
In one embodiment, the determining module 30 is further configured to obtain aortic root pressure;
performing index calculation according to the aortic root pressure, the predicted outlet pressure drop and the contrast agent flowing time, and determining a microcirculation resistance index of the coronary artery;
after determining the microcirculation resistance index of the coronary artery according to the predicted outlet pressure drop and the contrast agent flowing time, the method further comprises:
when the microcirculation resistance index exceeds a target index range, generating alarm information according to the microcirculation resistance index;
and sending the alarm information to the user terminal for alarm.
Because the device adopts all the technical schemes of all the embodiments, the device at least has all the beneficial effects brought by the technical schemes of the embodiments, and the description is omitted here.
In addition, the embodiment of the invention also provides a storage medium, wherein a micro-circulation resistance index calculation program is stored on the storage medium, and the micro-circulation resistance index calculation program realizes the steps of the micro-circulation resistance index calculation method when being executed by a processor.
Because the storage medium adopts all the technical schemes of all the embodiments, the storage medium has at least all the beneficial effects brought by the technical schemes of the embodiments, and the description is omitted here.
It should be noted that the above-described working procedure is merely illustrative, and does not limit the scope of the present invention, and in practical application, a person skilled in the art may select part or all of them according to actual needs to achieve the purpose of the embodiment, which is not limited herein.
In addition, technical details not described in detail in this embodiment may refer to the method for calculating the microcirculation resistance index provided in any embodiment of the present invention, which is not described herein.
Furthermore, it should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of embodiments, it will be clear to a person skilled in the art that the above embodiment method may be implemented by means of software plus a necessary general hardware platform, but may of course also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. Read Only Memory (ROM)/RAM, magnetic disk, optical disk) and comprising several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (10)
1. A method of calculating a microcirculation resistance index, the method comprising:
performing contour transformation on a coronary three-dimensional model of a coronary artery to obtain a plurality of three-dimensional contour lines of the coronary artery;
carrying out outlet information prediction according to a plurality of three-dimensional contour lines, coronary boundary information of the coronary arteries and a target pressure drop prediction model, so as to obtain predicted outlet pressure drop of the coronary arteries, wherein the target pressure drop prediction model is obtained by training a deep learning network based on a sample coronary artery set;
determining a microcirculation resistance index of the coronary artery according to the predicted outlet pressure drop and the contrast agent flowing time.
2. The method of calculating the microcirculation resistance index according to claim 1, wherein the predicting the outlet information according to the plurality of three-dimensional contour lines, the coronary boundary information of the coronary artery and the target pressure drop prediction model to obtain the predicted outlet pressure drop of the coronary artery includes:
determining a plurality of three-dimensional point coordinates on each three-dimensional contour line according to the plurality of three-dimensional contour lines;
performing feature dimension reduction on a plurality of three-dimensional point coordinates on each three-dimensional contour line according to an encoder network to obtain first coordinate features on each three-dimensional contour line;
and inputting the first coordinate characteristics of each three-dimensional contour line, the coronary artery boundary information of the coronary artery and the position relation of each three-dimensional contour line to a target pressure drop prediction model, and predicting outlet information according to the first coordinate characteristics of each three-dimensional contour line, the boundary information and the position relation of each three-dimensional contour line by using the target pressure drop prediction model to obtain the predicted outlet pressure drop of the coronary artery.
3. The method of calculating the microcirculation resistance index according to claim 1, wherein the predicting the outlet information according to the plurality of three-dimensional contour lines, the coronary boundary information of the coronary artery and the target pressure drop prediction model to obtain the predicted outlet pressure drop of the coronary artery includes:
dividing the coronary three-dimensional model to obtain a plurality of coronary segmented models of the coronary artery;
determining an interface contour line of each coronary artery segmentation model in a plurality of three-dimensional contour lines of the coronary arteries;
performing feature dimension reduction on a plurality of three-dimensional point coordinates on each interface contour line according to the encoder network to obtain second coordinate features of each interface contour line;
and inputting second coordinate characteristics of each interface contour line, coronary artery boundary information of the coronary artery and the position relation of each interface contour line to a target pressure drop prediction model, and predicting outlet information according to the second coordinate characteristics of each interface contour line, the boundary information and the position relation of each interface contour line through the target pressure drop prediction model to obtain predicted outlet pressure drop of the coronary artery.
4. The method of calculating a microcirculation resistance index according to claim 1, wherein the predicting the outlet information according to the plurality of three-dimensional contour lines, coronary boundary information of the coronary arteries and a target pressure drop prediction model to obtain a predicted outlet pressure drop of the coronary arteries further comprises:
acquiring the blood vessel type of the coronary artery;
determining an inlet pressure, an inlet velocity and an inlet flow from the vessel type;
and determining coronary boundary information of the coronary artery according to the inlet pressure, the inlet speed and the inlet flow.
5. The method for calculating the microcirculation resistance index according to claim 1, wherein before the three-dimensional model of coronary artery is subjected to contour transformation to obtain a plurality of three-dimensional contour lines of coronary artery, the method further comprises:
acquiring a coronary angiography image sequence of a coronary artery;
image segmentation is carried out on the coronary angiography image sequence to obtain coronary vessel images with a plurality of angles;
and performing image alignment on the coronary vessel images at a plurality of angles to generate a coronary three-dimensional model of the coronary artery.
6. The method of calculating the microcirculation resistance index according to claim 1, further comprising, before determining the microcirculation resistance index of the coronary artery based on the predicted outlet pressure drop and contrast agent flow-through time:
determining a contrast agent image quantity from a coronary angiography image sequence of the coronary arteries; [ R11]
Acquiring a preset sampling frame rate;
and performing time calculation according to the number of the contrast agent images and the preset sampling frame rate, and determining the flowing time of the contrast agent.
7. The method of claim 1, wherein said determining the microcirculation resistance index of the coronary artery from the predicted outlet pressure drop and contrast agent flow time comprises:
acquiring aortic root pressure;
performing index calculation according to the aortic root pressure, the predicted outlet pressure drop and the contrast agent flowing time, and determining a microcirculation resistance index of the coronary artery;
after determining the microcirculation resistance index of the coronary artery according to the predicted outlet pressure drop and the contrast agent flowing time, the method further comprises:
when the microcirculation resistance index exceeds a target index range, generating alarm information according to the microcirculation resistance index;
and sending the alarm information to the user terminal for alarm.
8. A microcirculation resistance index computing device, characterized in that the microcirculation resistance index computing device comprises:
the transformation module is used for carrying out contour transformation on the coronary three-dimensional model of the coronary artery to obtain a plurality of three-dimensional contour lines of the coronary artery;
the prediction module is used for predicting outlet information according to a plurality of three-dimensional contour lines, coronary boundary information of the coronary arteries and a target pressure drop prediction model, so as to obtain predicted outlet pressure drop of the coronary arteries, wherein the target pressure drop prediction model is obtained by training a deep learning network based on a sample coronary artery set;
a processing module for determining a microcirculation resistance index of the coronary artery based on the predicted outlet pressure drop and contrast agent flow-through time.
9. A microcirculation resistance index computing device, the device comprising: a memory, a processor, and a microcirculation resistance index calculation program stored on the memory and executable on the processor, the microcirculation resistance index calculation program configured to implement the microcirculation resistance index calculation method according to any one of claims 1 to 7.
10. A storage medium having stored thereon a microcirculation resistance index calculation program which when executed by a processor implements the microcirculation resistance index calculation method according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311445557.1A CN117556726A (en) | 2023-11-02 | 2023-11-02 | Microcirculation resistance index calculating method, device, equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311445557.1A CN117556726A (en) | 2023-11-02 | 2023-11-02 | Microcirculation resistance index calculating method, device, equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117556726A true CN117556726A (en) | 2024-02-13 |
Family
ID=89810153
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311445557.1A Pending CN117556726A (en) | 2023-11-02 | 2023-11-02 | Microcirculation resistance index calculating method, device, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117556726A (en) |
-
2023
- 2023-11-02 CN CN202311445557.1A patent/CN117556726A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
AU2020244586B2 (en) | Method and system for sensitivity analysis in modeling blood flow characteristics | |
US20230360803A1 (en) | Methods and systems for predicting sensitivity of blood flow calculations to changes in anatomical geometry | |
CN108665462B (en) | Highly integrated annotation and segmentation system for medical imaging | |
US10622092B2 (en) | Method and system for facilitating physiological computations | |
CN107615335A (en) | medical image processing method and system | |
CN106456078A (en) | Method and system for machine learning based assessment of fractional flow reserve | |
CN108665449B (en) | Deep learning model and device for predicting blood flow characteristics on blood flow vector path | |
CN109524119B (en) | GAN-based fractional flow reserve prediction method, device, equipment and medium | |
US20200360088A1 (en) | System and methods for estimation of blood flow using response surface and reduced order modeling | |
CN109949300B (en) | Method, system and computer readable medium for anatomical tree structure analysis | |
CN116486211A (en) | Model training method, fractional flow reserve calculation method, device and equipment | |
CN116013533A (en) | Training method, evaluation method and system of hemodynamic evaluation model of coronary artery | |
CN117556726A (en) | Microcirculation resistance index calculating method, device, equipment and storage medium | |
Freiman et al. | A functionally personalized boundary condition model to improve estimates of fractional flow reserve with CT (CT‐FFR) | |
CN113995388B (en) | Fractional flow reserve calculation method and device, electronic equipment and readable storage medium | |
JP2022519876A (en) | Systems and methods that determine the flow of fluid through the conduit of interest | |
CN111297388B (en) | Fractional flow reserve measuring device | |
CN111627002A (en) | Coronary artery microvascular resistance index calculation device and method | |
CN117314836A (en) | Fractional flow reserve calculation method, apparatus, device and storage medium | |
Tanade et al. | Cloud computing to enable wearable-driven longitudinal hemodynamic maps | |
CN117313574A (en) | Microcirculation resistance index calculating method, device, equipment and storage medium | |
CN115496007A (en) | Method and device for determining blood flow mechanical energy loss, electronic equipment and medium | |
CN117594244A (en) | Blood flow parameter evaluation method, device, computer equipment, medium and product | |
CN117976155A (en) | Method and computer equipment for obtaining coronary artery functional parameters based on contrast agent tracing curve | |
CN112419308A (en) | Plaque evaluation method and device, electronic equipment and storage medium |
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 |