CN108451540A - A kind of blood flow reserve fraction measurement method and apparatus - Google Patents
A kind of blood flow reserve fraction measurement method and apparatus Download PDFInfo
- Publication number
- CN108451540A CN108451540A CN201710086765.5A CN201710086765A CN108451540A CN 108451540 A CN108451540 A CN 108451540A CN 201710086765 A CN201710086765 A CN 201710086765A CN 108451540 A CN108451540 A CN 108451540A
- Authority
- CN
- China
- Prior art keywords
- characteristic parameter
- blood flow
- flow reserve
- narrow
- blood vessel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000017531 blood circulation Effects 0.000 title claims abstract description 84
- 238000000691 measurement method Methods 0.000 title claims abstract description 18
- 210000004204 blood vessel Anatomy 0.000 claims abstract description 68
- 238000005259 measurement Methods 0.000 claims abstract description 49
- 238000000034 method Methods 0.000 claims abstract description 18
- 208000031481 Pathologic Constriction Diseases 0.000 claims abstract description 15
- 238000013528 artificial neural network Methods 0.000 claims description 48
- 210000004351 coronary vessel Anatomy 0.000 claims description 48
- 238000012549 training Methods 0.000 claims description 34
- 230000003902 lesion Effects 0.000 claims description 22
- 238000002591 computed tomography Methods 0.000 claims description 17
- 238000011144 upstream manufacturing Methods 0.000 claims description 15
- 230000004913 activation Effects 0.000 claims description 14
- 230000036262 stenosis Effects 0.000 claims description 8
- 208000037804 stenosis Diseases 0.000 claims description 8
- 239000008280 blood Substances 0.000 claims description 6
- 210000004369 blood Anatomy 0.000 claims description 6
- 230000001537 neural effect Effects 0.000 claims description 5
- 241000208340 Araliaceae Species 0.000 claims description 4
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 4
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 4
- 235000008434 ginseng Nutrition 0.000 claims description 4
- 210000001367 artery Anatomy 0.000 claims description 3
- 210000003462 vein Anatomy 0.000 claims description 3
- 239000000523 sample Substances 0.000 description 21
- 238000005516 engineering process Methods 0.000 description 18
- 238000010586 diagram Methods 0.000 description 9
- 208000029078 coronary artery disease Diseases 0.000 description 7
- 238000011161 development Methods 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000001435 haemodynamic effect Effects 0.000 description 4
- 229940124549 vasodilator Drugs 0.000 description 4
- 239000003071 vasodilator agent Substances 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000000644 propagated effect Effects 0.000 description 3
- 201000000057 Coronary Stenosis Diseases 0.000 description 2
- 206010011089 Coronary artery stenosis Diseases 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000013146 percutaneous coronary intervention Methods 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000003325 tomography Methods 0.000 description 2
- 238000011282 treatment Methods 0.000 description 2
- 230000002792 vascular Effects 0.000 description 2
- 206010020751 Hypersensitivity Diseases 0.000 description 1
- 230000001154 acute effect Effects 0.000 description 1
- 208000026935 allergic disease Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000002586 coronary angiography Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000000004 hemodynamic effect Effects 0.000 description 1
- 230000009610 hypersensitivity Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000013610 patient sample Substances 0.000 description 1
- 230000035790 physiological processes and functions Effects 0.000 description 1
- 230000003716 rejuvenation Effects 0.000 description 1
- 238000010408 sweeping Methods 0.000 description 1
- 208000011580 syndromic disease Diseases 0.000 description 1
- 238000002560 therapeutic procedure Methods 0.000 description 1
- 230000001988 toxicity Effects 0.000 description 1
- 231100000419 toxicity Toxicity 0.000 description 1
- 238000002604 ultrasonography Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/50—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications
- A61B6/504—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications for diagnosis of blood vessels, e.g. by angiography
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/02—Arrangements for diagnosis sequentially in different planes; Stereoscopic radiation diagnosis
- A61B6/03—Computed tomography [CT]
- A61B6/032—Transmission computed tomography [CT]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/50—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications
- A61B6/507—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications for determination of haemodynamic parameters, e.g. perfusion CT
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/52—Devices using data or image processing specially adapted for radiation diagnosis
- A61B6/5211—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data
- A61B6/5217—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data extracting a diagnostic or physiological parameter from medical diagnostic data
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/52—Devices using data or image processing specially adapted for radiation diagnosis
- A61B6/5211—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data
- A61B6/5229—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data combining image data of a patient, e.g. combining a functional image with an anatomical image
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- High Energy & Nuclear Physics (AREA)
- Physics & Mathematics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Optics & Photonics (AREA)
- Pathology (AREA)
- Radiology & Medical Imaging (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Pulmonology (AREA)
- Theoretical Computer Science (AREA)
- Vascular Medicine (AREA)
- Physiology (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention discloses a kind of blood flow reserve fraction measurement method and apparatus, wherein method includes：Obtain target patient blood vessel characteristic parameter coronarius, wherein the blood vessel characteristic parameter includes the vessel cross-sections radius of setting position and the narrow characteristic parameter in coronary stricture region；The blood vessel characteristic parameter is inputted to the blood flow reserve fraction measurement model pre-established, obtains the blood flow reserve score of the target patient.The present invention solves the problems, such as measurement blood flow reserve score, and time-consuming and it is high to require equipment calculating, can measure blood flow reserve score efficiently, accurately and in real time.
Description
Technical field
The present embodiments relate to technical field of medical image processing more particularly to a kind of blood flow reserve fraction measurement methods
And device.
Background technology
With the development of social economy and the change of human life style, the morbidity and mortality of Coronary Artery Lesions are in notable
Ascendant trend, and age of onset tends to rejuvenation, seriously threatens the life and health of people, so carrying out coronary artery disease to people
The prevention of change is very urgent.Meanwhile along with the fast development of modern technologies and the further investigation of medical science and exploration, mesh
Preceding prevention to Coronary Artery Lesions, diagnosing and treating etc. obtain development in an all-round way.
The current popular technological means for carrying out diagnostic assessment to Coronary Artery Lesions mainly has：It is coronary angiography, intravascular
Related art methods and the evaluation index such as ultrasound and blood flow reserve score.Wherein, blood flow reserve score (Fractional flow
Reserve, FFR) it is really to be applied to clinical function assessment index, it is current quantitative and the weight of fixed point evaluation coronary artery physiological function
Want method.Moreover, FFR has been extensively examined the application value in various lesions, such as in coronary artery Single vessel disease, branched disease
Change, Left main stem disease, diffuses cascade lesion, bifurcated lesions, acute coronary artery syndrome, borderline lesion, percutaneous hat at bifurcated lesions
Shape arterial Interventional Therapy (percutaneous coronary intervention, PCI) effect assessment and combines that other are auxiliary afterwards
Help technological guidance's coronary heart disease (coronary heart disease, CHD) treatment etc., the application especially in borderline lesion
It is relatively broad, scientific basis is provided for CHD optimization treatments, meets the development trend of new era coronary intervention.
Currently, FFR measuring techniques include mainly two kinds, one is invasive FFR technologies, another kind is to be based on haemodynamics
The noninvasive FFR technologies of emulation.But there are operation risks for invasive FFR technologies, have certain toxicity using vasodilator, and
It is possible that cause patient of hypersensitivity, it is expensive；Although based on haemodynamics emulation noninvasive FFR technologies have it is noninvasive, economical,
The features such as repeatable strong, accuracy rate is high and provides information more comprehensively, but its is computationally intensive, needs high-performance computer, takes
It is long, it can not accomplish the requirement measured in real time.
Invention content
In view of this, the purpose of the present invention is to propose to a kind of blood flow reserve fraction measurement method and apparatus, to solve to measure
Time-consuming and requires high problem to equipment calculating for blood flow reserve score.
To achieve the above object, the present invention adopts the following technical scheme that：
On the one hand, an embodiment of the present invention provides a kind of blood flow reserve fraction measurement methods, including：
Obtain target patient blood vessel characteristic parameter coronarius, wherein the blood vessel characteristic parameter includes setting position
The vessel cross-sections radius at place and the narrow characteristic parameter in coronary stricture region, the narrow characteristic parameter are used
Blood vessel structure information at embodiment hemadostewnosis；
The blood vessel characteristic parameter is inputted to the blood flow reserve fraction measurement model pre-established, obtains the target patient
Blood flow reserve score.
On the other hand, an embodiment of the present invention provides a kind of blood flow reserve fraction measurement devices, including：
Blood vessel feature acquisition module, for obtaining target patient blood vessel characteristic parameter coronarius, wherein the blood vessel
Characteristic parameter includes the vessel cross-sections radius of setting position and the narrow feature ginseng in coronary stricture region
Number, the narrow characteristic parameter are used to embody the blood vessel structure information at hemadostewnosis；
Measurement model establishes module, for pre-establishing blood flow reserve fraction measurement model；
Blood flow reserve fraction measurement module, for the blood vessel characteristic parameter to be inputted the blood flow reserve score pre-established
Measurement model obtains the blood flow reserve score of the target patient.
The beneficial effects of the invention are as follows：Blood flow reserve fraction measurement method and apparatus provided in an embodiment of the present invention, pass through
Blood flow reserve fraction measurement model is pre-established, when carrying out Coronary Artery Lesions diagnosis to new patient, directly by the blood vessel of new patient
Characteristic parameter inputs the blood flow reserve fraction measurement model pre-established, can quickly and accurately export the coronal dynamic of new patient
The narrow blood flow reserve score of arteries and veins.Compared with invasive FFR technologies, the present invention is noninvasive FFR technologies, avoids operation risk, nothing
Vasodilator need to be used；Compared with the noninvasive FFR technologies emulated based on haemodynamics, the present invention calculates equipment and requires
It is low, home computer need to be only used, can quickly be calculated, it is time-consuming short, it can accomplish the requirement measured in real time.
Description of the drawings
Exemplary embodiments of the present invention will be described in detail referring to the drawings by general below, makes those skilled in the art
The above-mentioned and other feature and advantage for becoming apparent from the present invention, in attached drawing：
Fig. 1 is the flow diagram of blood flow reserve fraction measurement method provided in an embodiment of the present invention；
Fig. 2 is the flow diagram of another blood flow reserve fraction measurement method provided in an embodiment of the present invention；
Fig. 3 is the flow diagram provided in an embodiment of the present invention for establishing blood flow reserve fraction measurement model method；
Fig. 4 is the structural schematic diagram of neural network provided in an embodiment of the present invention；
Fig. 5 is the structure diagram of blood flow reserve fraction measurement device provided in an embodiment of the present invention.
Specific implementation mode
Technical solution to further illustrate the present invention below with reference to the accompanying drawings and specific embodiments.It is appreciated that
It is that specific embodiment described herein is used only for explaining the present invention rather than limitation of the invention.It further needs exist for illustrating
, only the parts related to the present invention are shown for ease of description, in attached drawing rather than entire infrastructure.
Fig. 1 is the flow diagram of blood flow reserve fraction measurement method provided in an embodiment of the present invention.This method is suitable for
The case where non-invasive measurement blood flow reserve score, this method can be executed by blood flow reserve fraction measurement device.The device can be with
It is realized by the mode of software and/or hardware, which is configured in computer.As shown in Figure 1, this method includes：
Step 110 obtains target patient blood vessel characteristic parameter coronarius.
Wherein, blood vessel characteristic parameter includes the vessel cross-sections radius and coronary stricture of setting position
The narrow characteristic parameter in region, the narrow characteristic parameter are used to embody the blood vessel structure information at hemadostewnosis.
Optionally, the vessel cross-sections radius of setting position can be that the coronary artery computerized tomography of target patient is swept
The vessel cross-sections radius of tracing multiple selected layer as in；Narrow characteristic parameter may include narrow width proximal radius, narrow most smaller part
Diameter, narrow remote end radius, entrance length, least radius length, outlet length and percentage diameter group reduce ratio.Wherein, entrance
Length be along on direction of the coronary artery far from heart, from the narrow beginning to the beginning of narrow least radius segment blood
The length of tube hub line；Least radius length is from the beginning of narrow least radius segment to the vessel centerline end
Length；It is to be opened from the end of narrow least radius segment to narrow along on direction of the coronary artery far from heart to export length
The length of vessel centerline between end；Percentage diameter group reduces ratio and is represented by：Wherein, rsTable
Show narrow least radius, rpIndicate the normal radius of blood vessel near narrow width proximal, rdIndicate near narrow remote end blood vessel just
Normal radius, wherein with the internal diameter of vascular wall to refer to, it is hemadostewnosis region, internal diameter contracting that internal diameter, which reduces degree more than 10%,
Small degree is blood vessel normal region no more than 10%, and the vessel radius in the region is the normal radius of blood vessel.
Blood vessel characteristic parameter is inputted the blood flow reserve fraction measurement model pre-established by step 120, obtains target patient
Blood flow reserve score.
Optionally, all blood vessel characteristic parameters in step 110 can be combined by this operation constitutes a feature vector,
This feature vector is inputted to the blood flow reserve fraction measurement model pre-established, directly obtains the blood flow reserve score of target patient
Value.Wherein, blood flow reserve fraction measurement model can be built based on neural network.For example, history Coronary Artery Lesions can be used
The diagnostic data of patient is trained neural network, obtains blood flow reserve fraction measurement model.
Blood flow reserve fraction measurement method provided in this embodiment as a result, by pre-establishing blood flow reserve fraction measurement
The blood vessel characteristic parameter of new patient is directly inputted the blood pre-established by model when carrying out Coronary Artery Lesions diagnosis to new patient
Stream deposit fraction measurement model, can quickly and accurately export the blood flow reserve score of the coronary artery stenosis of new patient.And have
Wound FFR technologies are compared, and the present invention is noninvasive FFR technologies, operation risk is avoided, without using vasodilator；With based on blood
Hydromechanics emulation noninvasive FFR technologies compare, the present invention to equipment calculating require it is low, only need to use home computer,
Quickly calculate, it is time-consuming short, it can accomplish the requirement measured in real time.
Fig. 2 is the flow diagram of another blood flow reserve fraction measurement method provided in an embodiment of the present invention.This implementation
Example is optimized based on above-described embodiment, and step is obtained target patient blood vessel characteristic parameter coronarius, is optimized for：
According to the Coronary artery computed tomography image of target patient, blood vessel characteristic parameter is obtained.
As shown in Fig. 2, blood flow reserve fraction measurement method provided in this embodiment includes：
Step 210, the Coronary artery computed tomography image according to target patient obtain blood vessel characteristic parameter.
Wherein, computerized tomography surface sweeping is the product that computer is combined with x-ray Examined effect, when highly collimated x-ray
When beam ring makees profile scanning (be typically cross section) around a certain position of human body, partial photonic is absorbed, x-ray intensity thus decay,
After unabsorbed photon penetrates human body, absorbed by detector, it is defeated as analog signal then through amplifying and being converted into electron stream
Enter electronic computer and carry out processing operation, is reconstructed into image.In the present embodiment, ct apparatus is to target patient
Coronary artery is scanned, and scan data is reconstructed into Coronary artery computed tomography image after computer is handled, at this point,
It can be based on image recognition technology, obtain target patient blood vessel characteristic parameter coronarius.Specifically, the operation may include：
A, according to Coronary artery computed tomography image, the vessel cross-sections radius of multiple selected layer is measured.
Optionally, the vessel cross-sections radius in each cross section of computed tomography images can be measured, is obtained
A part of the set of the vessel cross-sections radius arrived as blood vessel characteristic parameter.
B, identified from Coronary artery computed tomography image in coronary artery source location upstream and
Downstream it is narrow.
Wherein, source location is the every bit on the center line of the coronary artery, i.e. this operation can be known successively
Do not go out the narrow of each location point upstream and downstream in coronary artery, so as to the corresponding blood flow storage for obtaining each location point
Back-up number, so that whether accurate judgement target patient has Coronary Artery Lesions.Wherein, location point upstream indicates close since location point
One section of blood vessel of heart, location point downstream indicate one section of blood vessel far from heart since location point.
It is reference with the internal diameter of vascular wall, it is that blood vessel is narrow that internal diameter, which reduces degree more than 10%, as described in above-described embodiment
Narrow region, so as to identify the narrow of source location upstream and downstream in coronary artery.
C, the descending sequence of degree is reduced according to narrow diameter, respectively to the narrow of source location upstream and downstream
It is ranked up.
D, respectively from source location upstream and downstream it is narrow in select the forward at least one target stenosis of sorting.
Optionally, for a location point, can from its upstream and downstream it is narrow in respectively select four forward targets of sequence
It is narrow, in the case of ensureing that calculation amount is smaller, the accuracy of export structure is improved as possible.
E, the narrow characteristic parameter of target stenosis is extracted.
Blood vessel characteristic parameter is inputted the blood flow reserve fraction measurement model pre-established by step 220, obtains target patient
Blood flow reserve score.
The present embodiment obtains blood vessel feature ginseng according to the Coronary artery computed tomography image of target patient as a result,
Number, the blood vessel characteristic parameter that convenient can accurately get target patient further increase the effect of blood flow reserve fraction measurement
Rate.
Fig. 3 is the flow diagram provided in an embodiment of the present invention for establishing blood flow reserve fraction measurement model method.Such as Fig. 3
Shown, this method may include：
Step 310 obtains training sample set.
Wherein, training sample set may include multiple Coronary Artery Lesions patients sample vessel characteristic parameter coronarius and
Corresponding sample blood flow reserve score.Optionally, the preceding coronary artery for carrying out Coronary Artery Lesions diagnosis is sick for it by multiple Coronary Artery Lesions patients
Become patient, sample number be more than 500 people, can equally from the Coronary artery computed tomography image of Coronary Artery Lesions patient,
Obtain sample vessel characteristic parameter, and the composition of the sample vessel characteristic parameter and the blood vessel characteristic parameter described in above-described embodiment
It is identical；Sample blood flow reserve score can be the invasive blood flow reserve score of each Coronary Artery Lesions patient.
Step 320, structure neural network.
Specifically, it is each that the input layer of neural network, at least one hidden layer, activation primitive, output layer and each layer can be arranged
The initial parameter of node, wherein input layer includes node corresponding with blood vessel characteristic parameter, and at least one hidden layer includes multiple
Node, output layer include a node.
Optionally, activation primitive is Sigmoid functions, and output layer includes correcting linear unit, i.e. activation primitive isOutput layer includes (0, x) linear activation primitive f (x)=max, i.e., as x ＜ 0, f (x)=0, when x >=0
When, f (x)=x.The initial parameter of each each node of layer can be initialized by computer random.It is hidden in addition, hidden layer can be four layers
Layer, as shown in figure 4, neural network includes 10, four layers of hidden layer 20 of input layer and output layer 30.Wherein, edge is input to output
On direction, the number of nodes of each hidden layer is respectively 256,64,16 and 4.Optionally, the neural network of the present embodiment is full connection god
Through network, i.e. each node of preceding layer is connect with all nodes of later layer.For the neural network, n-th layer and (n+1)th
Layer relationship can be：xn+1=f (W(n)xn+b(n)), wherein xnIt is a vector, i-th of element indicates the i-th of n-th layer
Value on a node；xn+1It is a vector, i-th of element indicates the value on (n+1)th layer of i-th of node；On function f is
State Sigmoid functions；W(n)And b(n)It is node parameter, wherein W(n)It is the weight matrix of n-th layer, b(n)It is being biased towards for n-th layer
Amount, training neural network are exactly to train W(n)And b(n)Optimal value.
Step 330 is based on training sample set, training neural network.
Illustratively, using sample vessel characteristic parameter as the input of neural network, using sample blood flow reserve score as
The desired output of neural network, repetition training neural network, until obtaining the optimized parameter of each node of each layer.
Specifically, first, the cost function for defining entire neural network is：
Wherein, x(m)It is the blood vessel characteristic parameter of m-th of patient, the coronary artery computer of i-th of vessel cross-sections is disconnected
The blood vessel characteristic parameter obtained in layer scan image is x(i), corresponding invasive FFR values are y(i)；y(m)It is the invasive of m-th patient
FFR values；(x(m),y(m)) be m-th of patient sample；M is for trained sample number；M is m-th of patient；N is neural network
Total number of plies；N indicates the n-th layer of neural network；snIndicate the node number of n-th layer in neural network；Indicate nerve net
I-th of node of network n-th layer is to the weights between (n+1)th layer of j-th of node；F is sigmoid functions, and f ' expressions f is led
Number；h(x(m)) it is x(m)The value obtained after entire neural computing.
Then, the local derviation numerical value of above-mentioned cost function J is calculated using back-propagation algorithmWithIt is exemplary
, give a patient's sample (x(m),y(m)), we carry out propagated forward operation first, calculate swashing for each layer in neural network
Value living and output valve h (x(m)).Then, for the node i of n-th (2≤n ＜ N) layer, we calculate its residual errorIt should
Residual error shows how many influence produced on the residual error of final output value for the node.For final output node, we can be with
The gap between the activation value that neural network generates and actual value is directly calculated, this gap definition is by we(n-th layer
Indicate output layer).For hidden layer, we can use the weighted average of node residual error to calculate
Optionally, the activation value of each layer can utilize propagated forward formula to calculate in above-mentioned neural network, and the propagated forward is public
Formula includes：
z(2)=W(1)x+b(1) (1)
a(n+1)=f (z(n+1)), n >=1 (2)
z(n+1)=W(n)a(n)+b(n), n >=2 (3)
Wherein, x is the blood vessel characteristic parameter of input, a(n)Indicate the activation value of n-th layer.As a result, by formula (1), (2) and
(3) every layer of activation value can be obtained.
It can be calculated accordingly, for n-th layer (output layer)：
δ(N)=-(y-a(N))*′(z(N)) (4)
Wherein, y is the invasive FFR values of output.
N-th (2≤n ＜ N) layer can be calculated：
δ(n)=((W(n))Tδ(n+1))*f′(z(n)) (5)
Reference formula (4) and (5) can calculate the local derviation numerical value of cost function J, respectively：
Finally, each node parameter is updated according to the local derviation numerical value of cost function J.Specifically, setting full null matrix Δ W(n)With
Full null vector Δ b(n), wherein Δ W(n)And W(n)Dimension it is identical, Δ b(n)And b(n)Dimension it is identical.Calculating cost function
After the local derviation numerical value of J, by Δ W(n)It is updated toBy Δ b(n)It is updated toFinally,
Utilize updated Δ W(n)With Δ b(n)Node parameter is updated, e.g., by W(n)It is updated toBy b(n)It is updated toWherein, the value of α can be
0.01, thus repetition training neural network, finally obtains optimal W(n)And b(n)。
Step 340, using the neural network after the completion of training as blood flow reserve fraction measurement model.
The blood flow reserve fraction measurement method provided by above-described embodiment, by a large amount of clinical trials, this method obtains
FFR values and it is existing based on haemodynamics noninvasive FFR technologies (FFR-CT) output FFR values comparison after difference it is little
In 0.01, therefore, the consistency of this programme and FFR-CT are good.
Blood flow reserve fraction measurement method provided in this embodiment, by pre-establishing blood flow reserve fraction measurement model,
When carrying out Coronary Artery Lesions diagnosis to new patient, the blood vessel characteristic parameter of new patient is directly inputted to the blood flow reserve pre-established
Fraction measurement model can quickly and accurately export the blood flow reserve score of the coronary artery stenosis of new patient.With invasive FFR
Technology is compared, and the present invention is noninvasive FFR technologies, operation risk is avoided, without using vasodilator；With based on hemodynamic
Learn emulation noninvasive FFR technologies compare, the present invention to equipment calculating require it is low, only need to use home computer, can quickly count
It calculates, it is time-consuming short, it can accomplish the requirement measured in real time.
Fig. 5 is the structure diagram of blood flow reserve fraction measurement device provided in an embodiment of the present invention.As shown in figure 5, the dress
It sets and establishes module 2 and blood flow reserve fraction measurement module 3 including blood vessel feature acquisition module 1, measurement model.
Wherein, blood vessel feature acquisition module 1 is for obtaining target patient blood vessel characteristic parameter coronarius, wherein blood
Pipe characteristic parameter includes the vessel cross-sections radius of setting position and the narrow feature ginseng in coronary stricture region
Number, the narrow characteristic parameter are used to embody the blood vessel structure information at hemadostewnosis；
Measurement model establishes module 2 for pre-establishing blood flow reserve fraction measurement model；
Blood flow reserve fraction measurement module 3 is used to blood vessel characteristic parameter inputting the blood flow reserve fraction measurement pre-established
Model obtains the blood flow reserve score of target patient.
Optionally, above-mentioned blood vessel feature acquisition module 1 may include：
Blood vessel feature acquiring unit obtains blood for the Coronary artery computed tomography image according to target patient
Pipe characteristic parameter.
In the present embodiment, blood vessel feature acquiring unit may include：
Vessel cross-sections radius measures subelement, for according to Coronary artery computed tomography image, measuring multiple
The vessel cross-sections radius of selected layer；
Narrow identification subelement, for being identified in coronary artery from Coronary artery computed tomography image
Source location upstream and downstream it is narrow, wherein source location be coronary artery center line on every bit；
Narrow sorting subunit, for reducing the descending sequence of degree according to narrow diameter, respectively to target location
Point the narrow of upstream and downstream is ranked up；
Narrow selection subelement, for respectively from source location upstream and downstream it is narrow in select sequence it is forward to
A few target stenosis；
Narrow characteristic parameter subelement, the narrow characteristic parameter for extracting target stenosis.
Based on said program, the measurement model of the present embodiment is established module 3 and be may include：
Training sample set acquiring unit, for obtaining training sample set, wherein training sample set includes multiple hats
The sample vessel characteristic parameter coronarius and corresponding sample blood flow reserve score of arteries and veins lesion patient；
Neural network construction unit, for building neural network；
Neural metwork training unit, for being based on training sample set, training neural network；
Measurement model determination unit, for using the neural network after the completion of training as blood flow reserve fraction measurement model.
Optionally, above-mentioned neural network construction unit can be specifically used for：
The initial of the input layer of neural network, at least one hidden layer, activation primitive, output layer and each node of each layer is set
Parameter, wherein input layer includes node corresponding with blood vessel characteristic parameter, and at least one hidden layer includes multiple nodes, output
Layer includes a node.
Wherein, activation primitive can be Sigmoid functions, and output layer may include correcting linear unit.
Optionally, above-mentioned neural metwork training unit can be specifically used for：
Using sample vessel characteristic parameter as the input of neural network, using sample blood flow reserve score as neural network
Desired output, repetition training neural network, until obtaining the optimized parameter of each node of each layer.
Blood flow reserve fraction measurement device provided in this embodiment, the blood flow reserve provided with any embodiment of the present invention
Fraction measurement method belongs to same inventive concept, can perform the blood flow reserve fraction measurement side that any embodiment of the present invention is provided
Method has corresponding function and advantageous effect.The not technical detail of detailed description in the present embodiment, reference can be made to the present invention is arbitrary
The blood flow reserve fraction measurement method that embodiment provides.
Note that above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The present invention is not limited to specific embodiments described here, can carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out to the present invention by above example
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
May include other more equivalent embodiments, and the scope of the present invention is determined by scope of the appended claims.
Claims (14)
1. a kind of blood flow reserve fraction measurement method, which is characterized in that including：
Obtain target patient blood vessel characteristic parameter coronarius, wherein the blood vessel characteristic parameter includes setting position
Vessel cross-sections radius and the narrow characteristic parameter in coronary stricture region, the narrow characteristic parameter are used for body
Blood vessel structure information at existing hemadostewnosis；
The blood vessel characteristic parameter is inputted to the blood flow reserve fraction measurement model pre-established, obtains the blood of the target patient
Stream deposit score.
2. according to the method described in claim 1, it is characterized in that, acquisition target patient blood vessel feature ginseng coronarius
Number, including：
According to the Coronary artery computed tomography image of the target patient, the blood vessel characteristic parameter is obtained.
3. according to the method described in claim 2, it is characterized in that, the coronary artery computer according to the target patient
Tomoscan image obtains the blood vessel characteristic parameter, including：
According to the Coronary artery computed tomography image, the vessel cross-sections radius of multiple selected layer is measured；
From identified in the Coronary artery computed tomography image in coronary artery source location upstream and under
That swims is narrow, wherein source location is the every bit on the center line of the coronary artery；
The descending sequence of degree is reduced according to narrow diameter, the narrow of source location upstream and downstream is arranged respectively
Sequence；
Respectively from source location upstream and downstream it is narrow in select the forward at least one target stenosis of sorting；
Extract the narrow characteristic parameter of the target stenosis.
4. according to the method described in claim 1, it is characterized in that, pre-establish blood flow reserve fraction measurement model, including：
Obtain training sample set, wherein the training sample set includes the sample coronarius of multiple Coronary Artery Lesions patients
This blood vessel characteristic parameter and corresponding sample blood flow reserve score；
Build neural network；
Based on the training sample set, the training neural network；
Using the neural network after the completion of training as the blood flow reserve fraction measurement model.
5. according to the method described in claim 4, it is characterized in that, the structure neural network, including：
The initial of the input layer of the neural network, at least one hidden layer, activation primitive, output layer and each node of each layer is set
Parameter, wherein the input layer includes node corresponding with the blood vessel characteristic parameter, and at least one hidden layer includes more
A node, the output layer include a node.
6. according to the method described in claim 5, it is characterized in that, the activation primitive be Sigmoid functions, the output layer
Including correcting linear unit.
7. according to the method described in claim 5, it is characterized in that, described be based on the training sample set, the training god
Through network, including：
Using the sample vessel characteristic parameter as the input of the neural network, using the sample blood flow reserve score as institute
State the desired output of neural network, neural network described in repetition training, until obtaining the optimized parameter of each node of each layer.
8. a kind of blood flow reserve fraction measurement device, which is characterized in that including：
Blood vessel feature acquisition module, for obtaining target patient blood vessel characteristic parameter coronarius, wherein the blood vessel feature
Parameter includes the vessel cross-sections radius of setting position and the narrow characteristic parameter in coronary stricture region, institute
Narrow characteristic parameter is stated for embodying the blood vessel structure information at hemadostewnosis；
Measurement model establishes module, for pre-establishing blood flow reserve fraction measurement model；
Blood flow reserve fraction measurement module, for the blood vessel characteristic parameter to be inputted the blood flow reserve fraction measurement pre-established
Model obtains the blood flow reserve score of the target patient.
9. device according to claim 8, which is characterized in that the blood vessel feature acquisition module includes：
Blood vessel feature acquiring unit obtains institute for the Coronary artery computed tomography image according to the target patient
State blood vessel characteristic parameter.
10. device according to claim 9, which is characterized in that the blood vessel feature acquiring unit includes：
Vessel cross-sections radius measures subelement, for according to the Coronary artery computed tomography image, measuring multiple
The vessel cross-sections radius of selected layer；
Narrow identification subelement, for being identified in coronary artery from the Coronary artery computed tomography image
Source location upstream and downstream it is narrow, wherein source location be the coronary artery center line on it is each
Point；
Narrow sorting subunit, for reducing the descending sequence of degree according to narrow diameter, respectively on source location
Trip and the narrow of downstream are ranked up；
Narrow selection subelement, for respectively from source location upstream and downstream it is narrow in select sequence forward at least one
A target stenosis；
Narrow characteristic parameter subelement, the narrow characteristic parameter for extracting the target stenosis.
11. device according to claim 8, which is characterized in that the measurement model establishes module and includes：
Training sample set acquiring unit, for obtaining training sample set, wherein the training sample set includes multiple hats
The sample vessel characteristic parameter coronarius and corresponding sample blood flow reserve score of arteries and veins lesion patient；
Neural network construction unit, for building neural network；
Neural metwork training unit, for being based on the training sample set, the training neural network；
Measurement model determination unit, for using the neural network after the completion of training as the blood flow reserve fraction measurement model.
12. according to the devices described in claim 11, which is characterized in that the neural network construction unit is specifically used for：
The initial of the input layer of the neural network, at least one hidden layer, activation primitive, output layer and each node of each layer is set
Parameter, wherein the input layer includes node corresponding with the blood vessel characteristic parameter, and at least one hidden layer includes more
A node, the output layer include a node.
13. device according to claim 12, which is characterized in that the activation primitive is Sigmoid functions, the output
Layer includes correcting linear unit.
14. device according to claim 12, which is characterized in that the neural metwork training unit is specifically used for：
Using the sample vessel characteristic parameter as the input of the neural network, using the sample blood flow reserve score as institute
State the desired output of neural network, neural network described in repetition training, until obtaining the optimized parameter of each node of each layer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710086765.5A CN108451540B (en) | 2017-02-17 | 2017-02-17 | Fractional flow reserve measurement method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710086765.5A CN108451540B (en) | 2017-02-17 | 2017-02-17 | Fractional flow reserve measurement method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108451540A true CN108451540A (en) | 2018-08-28 |
| CN108451540B CN108451540B (en) | 2021-08-31 |
Family
ID=63228806
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710086765.5A Active CN108451540B (en) | 2017-02-17 | 2017-02-17 | Fractional flow reserve measurement method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108451540B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109288537A (en) * | 2018-11-01 | 2019-02-01 | 杭州晟视科技有限公司 | Assess system, method, equipment and the storage medium of blood flow reserve score |
| CN109326354A (en) * | 2018-11-09 | 2019-02-12 | 深圳市孙逸仙心血管医院（深圳市心血管病研究所） | Based on ANN blood flow reserve Score on Prediction method, apparatus, equipment and medium |
| CN109523515A (en) * | 2018-10-18 | 2019-03-26 | 深圳市孙逸仙心血管医院（深圳市心血管病研究所） | The calculation method of blood flow reserve score |
| CN109524119A (en) * | 2018-11-09 | 2019-03-26 | 深圳市孙逸仙心血管医院（深圳市心血管病研究所） | Based on GAN blood flow reserve Score on Prediction method, apparatus, equipment and medium |
| CN110584696A (en) * | 2019-09-20 | 2019-12-20 | 杭州晟视科技有限公司 | Fractional flow reserve assessment method and device and storage medium |
| CN111297388A (en) * | 2020-04-03 | 2020-06-19 | 中山大学 | Fractional flow reserve measurement method and device |
| CN111652881A (en) * | 2020-07-01 | 2020-09-11 | 杭州脉流科技有限公司 | Coronary artery reconstruction and fractional flow reserve calculation method, device and equipment based on deep learning and readable storage medium |
| CN112132203A (en) * | 2020-09-18 | 2020-12-25 | 中山大学 | Intravascular ultrasound image-based fractional flow reserve measurement method and system |
| CN114334160A (en) * | 2021-12-24 | 2022-04-12 | 北京阅影科技有限公司 | Method and device for solving vascular functional indexes and computer-readable storage medium |
| CN114330161A (en) * | 2021-12-16 | 2022-04-12 | 深圳市阅影科技有限公司 | Generation method and device of Fractional Flow Reserve (FFR) value determination model |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1551033A (en) * | 2003-03-20 | 2004-12-01 | ��ʽ���綫֥ | Processor for analyzing tubelike structure such as blood vessel |
| US7693909B2 (en) * | 2007-04-25 | 2010-04-06 | Siemens Medical Solutions Usa, Inc. | Method for integrating quantitative measurements of imaging systems with reporting applications of medical recording systems |
| CN101991420A (en) * | 2009-08-27 | 2011-03-30 | 上海西门子医疗器械有限公司 | Method and system for positioning suspected blood vessel narrow area |
| CN103646188A (en) * | 2013-12-27 | 2014-03-19 | 长春工业大学 | Non-invasive diagnostic method of coronary heart disease based on hybrid intelligent algorithm |
| CN104224217A (en) * | 2013-06-24 | 2014-12-24 | 株式会社东芝 | Method of, and apparatus for, processing medical image |
| CN104424629A (en) * | 2013-08-19 | 2015-03-18 | 深圳先进技术研究院 | X-ray chest radiography lung segmentation method and device |
| US20150112182A1 (en) * | 2013-10-17 | 2015-04-23 | Siemens Aktiengesellschaft | Method and System for Machine Learning Based Assessment of Fractional Flow Reserve |
| CN105078440A (en) * | 2014-05-09 | 2015-11-25 | 西门子公司 | Method and system for non-invasive computation of hemodynamic indices for coronary artery stenosis |
| CN105190693A (en) * | 2013-03-01 | 2015-12-23 | 波士顿科学国际有限公司 | Systems and methods for lumen border detection in intravascular ultrasound sequences |
| CN105934199A (en) * | 2013-11-21 | 2016-09-07 | 三星电子株式会社 | Apparatus and method for processing a medical image of a body lumen |
| WO2016159881A1 (en) * | 2015-03-31 | 2016-10-06 | Agency For Science, Technology And Research | Method and apparatus for assessing blood vessel stenosis |
| CN106037710A (en) * | 2014-11-24 | 2016-10-26 | 西门子公司 | Synthetic data-driven hemodynamic determination in medical imaging |
-
2017
- 2017-02-17 CN CN201710086765.5A patent/CN108451540B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1551033A (en) * | 2003-03-20 | 2004-12-01 | ��ʽ���綫֥ | Processor for analyzing tubelike structure such as blood vessel |
| US7693909B2 (en) * | 2007-04-25 | 2010-04-06 | Siemens Medical Solutions Usa, Inc. | Method for integrating quantitative measurements of imaging systems with reporting applications of medical recording systems |
| CN101991420A (en) * | 2009-08-27 | 2011-03-30 | 上海西门子医疗器械有限公司 | Method and system for positioning suspected blood vessel narrow area |
| CN105190693A (en) * | 2013-03-01 | 2015-12-23 | 波士顿科学国际有限公司 | Systems and methods for lumen border detection in intravascular ultrasound sequences |
| CN104224217A (en) * | 2013-06-24 | 2014-12-24 | 株式会社东芝 | Method of, and apparatus for, processing medical image |
| CN104424629A (en) * | 2013-08-19 | 2015-03-18 | 深圳先进技术研究院 | X-ray chest radiography lung segmentation method and device |
| US20150112182A1 (en) * | 2013-10-17 | 2015-04-23 | Siemens Aktiengesellschaft | Method and System for Machine Learning Based Assessment of Fractional Flow Reserve |
| CN105934199A (en) * | 2013-11-21 | 2016-09-07 | 三星电子株式会社 | Apparatus and method for processing a medical image of a body lumen |
| CN103646188A (en) * | 2013-12-27 | 2014-03-19 | 长春工业大学 | Non-invasive diagnostic method of coronary heart disease based on hybrid intelligent algorithm |
| CN105078440A (en) * | 2014-05-09 | 2015-11-25 | 西门子公司 | Method and system for non-invasive computation of hemodynamic indices for coronary artery stenosis |
| CN106037710A (en) * | 2014-11-24 | 2016-10-26 | 西门子公司 | Synthetic data-driven hemodynamic determination in medical imaging |
| WO2016159881A1 (en) * | 2015-03-31 | 2016-10-06 | Agency For Science, Technology And Research | Method and apparatus for assessing blood vessel stenosis |
Non-Patent Citations (3)
| Title |
|---|
| KWON，CHUNG，PARK等: "a novel patient-specific model to compute coronary fractional flow reserve", 《WEB OF SCIENCE》 * |
| 姚铭，刘萍，林少君: "《过程控制实验教程》", 30 September 2008, 厦门大学出版社 * |
| 马燕山: "人体动脉的计算流体力学模拟与分析", 《中国博士学位论文全文数据库医药卫生科技辑》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109523515A (en) * | 2018-10-18 | 2019-03-26 | 深圳市孙逸仙心血管医院（深圳市心血管病研究所） | The calculation method of blood flow reserve score |
| CN109288537B (en) * | 2018-11-01 | 2022-08-09 | 杭州晟视科技有限公司 | System, method, apparatus and storage medium for assessing fractional flow reserve |
| CN109288537A (en) * | 2018-11-01 | 2019-02-01 | 杭州晟视科技有限公司 | Assess system, method, equipment and the storage medium of blood flow reserve score |
| CN109326354A (en) * | 2018-11-09 | 2019-02-12 | 深圳市孙逸仙心血管医院（深圳市心血管病研究所） | Based on ANN blood flow reserve Score on Prediction method, apparatus, equipment and medium |
| CN109524119A (en) * | 2018-11-09 | 2019-03-26 | 深圳市孙逸仙心血管医院（深圳市心血管病研究所） | Based on GAN blood flow reserve Score on Prediction method, apparatus, equipment and medium |
| CN109524119B (en) * | 2018-11-09 | 2023-07-04 | 深圳市孙逸仙心血管医院（深圳市心血管病研究所） | GAN-based fractional flow reserve prediction method, device, equipment and medium |
| CN110584696A (en) * | 2019-09-20 | 2019-12-20 | 杭州晟视科技有限公司 | Fractional flow reserve assessment method and device and storage medium |
| CN111297388A (en) * | 2020-04-03 | 2020-06-19 | 中山大学 | Fractional flow reserve measurement method and device |
| CN111652881A (en) * | 2020-07-01 | 2020-09-11 | 杭州脉流科技有限公司 | Coronary artery reconstruction and fractional flow reserve calculation method, device and equipment based on deep learning and readable storage medium |
| CN112132203A (en) * | 2020-09-18 | 2020-12-25 | 中山大学 | Intravascular ultrasound image-based fractional flow reserve measurement method and system |
| CN112132203B (en) * | 2020-09-18 | 2023-09-29 | 中山大学 | Fractional flow reserve measurement method and system based on intravascular ultrasound image |
| CN114330161A (en) * | 2021-12-16 | 2022-04-12 | 深圳市阅影科技有限公司 | Generation method and device of Fractional Flow Reserve (FFR) value determination model |
| CN114334160A (en) * | 2021-12-24 | 2022-04-12 | 北京阅影科技有限公司 | Method and device for solving vascular functional indexes and computer-readable storage medium |
| CN114334160B (en) * | 2021-12-24 | 2023-11-28 | 北京阅影科技有限公司 | Method, device and computer readable storage medium for solving vascular function index |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108451540B (en) | 2021-08-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108451540A (en) | A kind of blood flow reserve fraction measurement method and apparatus | |
| CN110853029B (en) | Method, system, and medium for automatically predicting blood flow characteristics based on medical images | |
| US11707196B2 (en) | Automated measurement system and method for coronary artery disease scoring | |
| CN106659400B (en) | Device for determining a fractional flow reserve value | |
| CN107978371B (en) | Method and system for rapidly calculating micro-circulation resistance | |
| JP6667999B2 (en) | Image processing apparatus, image processing method, and program | |
| CN111134651B (en) | Method, device and system for calculating fractional flow reserve based on intracavity images and computer storage medium | |
| Baumann et al. | Coronary CT angiography-derived fractional flow reserve correlated with invasive fractional flow reserve measurements–initial experience with a novel physician-driven algorithm | |
| CN108665449B (en) | Deep learning model and device for predicting blood flow characteristics on blood flow vector path | |
| JP7118464B2 (en) | Method and apparatus for acquiring vascular pressure difference | |
| CN109378076A (en) | For carrying out the method and system of sensitivity analysis in blood flow characteristic models | |
| JP2017500179A (en) | A method for assessing stenosis severity by stenosis mapping | |
| CN108742587B (en) | Method and device for acquiring blood flow characteristic value based on medical history information | |
| CN109036551A (en) | A kind of coronary artery physiologic index relationship is established and application method, device | |
| US11039804B2 (en) | Apparatus and method for determining a fractional flow reserve | |
| CN108717874B (en) | Method and device for obtaining blood vessel pressure value based on specific physiological parameters | |
| Liu et al. | Physiologically personalized coronary blood flow model to improve the estimation of noninvasive fractional flow reserve | |
| CN114947910A (en) | Coronary artery end microvascular resistance calculation method and FFR calculation method and system | |
| WO2020083390A1 (en) | Method, device and system for acquiring blood flow of large artery on heart surface, and storage medium | |
| CN111297388B (en) | Fractional flow reserve measuring device | |
| US20210290076A1 (en) | System and a method for determining a significance of a stenosis | |
| US10332255B2 (en) | Method for assessing stenosis severity in a lesion tree through stenosis mapping | |
| JP6675458B2 (en) | Blood vessel analysis device, blood vessel analysis method, and blood vessel analysis program | |
| Saveljic et al. | Numerical simulation of fractional flow reserve in atherosclerotic coronary arteries | |
| Overman | Artificial Intelligence Tool May Help Prevent Heart Attacks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |