CN109326354A - Based on ANN blood flow reserve Score on Prediction method, apparatus, equipment and medium - Google Patents
Based on ANN blood flow reserve Score on Prediction method, apparatus, equipment and medium Download PDFInfo
- Publication number
- CN109326354A CN109326354A CN201811333927.1A CN201811333927A CN109326354A CN 109326354 A CN109326354 A CN 109326354A CN 201811333927 A CN201811333927 A CN 201811333927A CN 109326354 A CN109326354 A CN 109326354A
- Authority
- CN
- China
- Prior art keywords
- blood flow
- image
- flow reserve
- reserve score
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
Abstract
Present invention discloses one kind to be based on ANN blood flow reserve Score on Prediction method, apparatus, equipment and medium, and step includes: that all basic datas in benchmark database are divided into modeling data and model inspection data according to designated ratio；The modeling data is trained by assignment algorithm and obtains blood flow reserve Score on Prediction model；The blood flow reserve Score on Prediction model is checked by model inspection data；Judge whether checking computation results meet specified requirement；If so, using the blood flow reserve score of the blood flow reserve Score on Prediction model prediction tester.It can accurately predict blood flow reserve score, accuracy highest can reach 98%, and bat can reach 90% or more；Have a wide range of application, needn't know that the relationship between input parameter and reference data on formula can be predicted there is bigger freedom degree.
Description
Technical field
The present invention relates to medical science, especially relate to it is a kind of based on ANN blood flow reserve Score on Prediction method,
Device, equipment and medium.
Background technique
Coronarography and intravascular ultrasound are regarded as " goldstandard " of diagnosis of coronary heart disease, but they can only be to disease
Become stenosis carry out imaging evaluation, and it is narrow on earth on Distal blood flow produce it is much influence it is unknown；Blood flow storage
Back-up number (FFR) now has become the generally acknowledged index of coronary stenosis Evaluation of Functional, and most important function is unknown to one
The functional consequence of the coronary stenosis of influence carries out accurate evaluation.
Blood flow reserve score (FFR) refers to that in coronary artery, target measurement blood vessel is supplied there are in the case where stenotic lesion
The obtainable maximum blood flow of myocardial region and the same area theoretically can be obtained the ratio between maximum blood flow under normal circumstances.
FFR is mainly obtained by calculating the ratio between coronary artery stenosis remote pressure and aortic root pressure.Narrow remote end pressure can
With by Pressure wire maximum perfusion blood flow (by coronary artery or intravenous injection papaverine or adenosine or ATP) when measure.
(Pd is the coronary stenosis remote pressure of guiding catheter measurement to FFR=Pd/Pa, and Pa is the active of Pressure wire measurement
Pulse pressure) in general, FFR refers under maximum congestive state, and " tranquillization FFR " this concept is not present.
For normal epicardial coronary arteries to the resistance very little of blood flow, the normal value of FFR is 1.0；The value of FFR will be less than
Show that current Epicardial coronary arteries have the presence of stenotic lesion when 1.0.
When the case where FFR < 0.75, representative narrow situation nearly all will lead to myocardial ischemia, the feelings of FFR >=0.75
A possibility that when condition, representative is narrow, causes myocardial ischemia is very small.
Coronary artery CTA energy accurate evaluation Severity of Coronary Artery Stenosis, and can distinguish tube wall patch property, it is a kind of noninvasive, operation letter
Single Row CT Coronary Angiography for Coronary Artery inspection method, can be used as the prefered method of screening people at highest risk.Therefore, if for coronary heart disease
The blood vessel of patient is intervened, and early period should carry out the evaluation of CTA to Coronary Artery in patients.Chronic total occlusion of coronary artery
(CTO) if evaluated using CTA, evaluation result has some valuable information certainly.
It is not only examined without additional image by the FFR (CTFFR) that coronary artery CT angiography CCTA calculates noninvasive acquisition
It looks into or drug, good with the FFR correlation that measures when radiography, this integrated technique can fundamentally avoid unnecessary coronary artery
Angiography and revascularization are treated.DeFacto test result it also clearly appears that in coronary artery CT, CTFFR result
Analysis provides those and really limits blood flow and increase the physiologic information of the lesion of patient's risk.CTFFR combines coronary artery CTA
With the advantage of FFR, coronary artery stenosis can be assessed in terms of structure and function two, a kind of offer Coronary Artery Lesions dissection is provided
Learn the brand-new Non-invaive examination system with function assessment information.
But existing detection architecture is general to the accuracy in computation of blood flow storage score, and needs to carry out cumbersome calculating
To obtain blood flow storage score, take time and effort.
Summary of the invention
The main object of the present invention is to provide one kind based on ANN blood flow reserve Score on Prediction method, apparatus, equipment and Jie
Matter, to solve at least one technical problem proposed in background technique.
It is a kind of based on ANN blood flow reserve Score on Prediction method that the present invention proposes that the present invention proposes, includes the following steps:
All basic datas in benchmark database are divided into modeling data and model inspection data according to designated ratio；
Above-mentioned modeling data is trained by assignment algorithm and obtains blood flow reserve Score on Prediction model；
Above-mentioned blood flow reserve Score on Prediction model is checked by model inspection data；
Judge whether checking computation results meet specified requirement；
If so, using the blood flow reserve score of above-mentioned blood flow reserve Score on Prediction model prediction tester.
Further, will own in benchmark database above-mentioned based in ANN blood flow reserve Score on Prediction method
Before the step of basic data is divided into modeling data and model inspection data according to designated ratio, further comprise the steps of:
Benchmark database is established,
Wherein, the step of establishing benchmark database, comprising:
Obtain specified quantity tester to Color Sonography image or CT image and its corporal characteristic information；
By above-mentioned Color Sonography image or CT image, the blood flow reserve score of each tester is calculated；
The corporal characteristic information of each tester, Color Sonography image or CT image and blood flow reserve score are carried out same
Step pairing, obtains basic data；
By the above-mentioned foundation data conformity of each tester, said reference database is obtained.
Further, above-mentioned based in ANN blood flow reserve Score on Prediction method, above by above-mentioned Color Sonography figure
As or CT image, the step of calculating the blood flow reserve score of each tester, comprising:
Above-mentioned Color Sonography image or CT image are split, and cardiac image is obtained by morphological operation, to upper
It states cardiac image progress histogram analysis and obtains ventricular atrial image, make the difference to obtain the heart by cardiac image and ventricular atrial image
Flesh image；
Morphological dilations are carried out to the binary image of aorta images, obtain the bianry image of full aorta, and pass through
Pixel negates to obtain full aorta complementary image, carries out region growing according to the average gray put on aorta center line, obtains
Aorta images containing coronary ostium do figure with the aorta images containing coronary ostium and full aorta complementary image
As multiplication, the image containing coronary ostium is obtained, and determines coronary ostium；
Using coronary ostium as seed point on myocardium image, coronary artery is extracted by region growing, is calculated coronal dynamic
The average gray and average variance of arteries and veins extract coronary artery tree along coronary artery direction according to coronary artery intensity profile；
Coronary artery images are subjected to binaryzation, then draw iso-surface images, obtain coronary artery three-dimensional grid image；
With numerical methods of solving continuity and Navier-Stokes equation:
Wherein,P, ρ, μ are respectively flow velocity, pressure, blood flow density, blood flow viscosity, and ▽ indicates gradient, when t indicates unit
Between, the transposition of T representing matrix；
Entrance boundary condition are as follows: Paorta- 13mm mercury column-P0, wherein P0Zero stream pressure of position；
The calculating of resistance to flow output boundary condition are as follows:
Wherein, QtotalIt is myocardial volume multiplied by myocardial blood flow density, (Qoutlet)iFor the blood flow for exporting i, DiFor outlet i's
Diameter, (Routlet)iFor the assistant for exporting i, coronary flow reserve CFR is set as 2.7；
Calculate the pressure (P of each point in three-dimensional networkoutlet)i, and it is calculated by the following formula blood flow reserve score FFR；
Wherein, PaortaIt is AoMP, (Poutlet)iIt is the pressure value of three-dimensional grid image midpoint i.
Further, above-mentioned based in ANN blood flow reserve Score on Prediction method, by the corporal characteristic of each tester
The step of information, Color Sonography image or CT image and blood flow reserve score synchronize pairing, obtain basic data, packet
It includes:
The above-mentioned cardiac image of each tester and ventricular atrial image filtering are handled；
The Color Sonography image of each tester or CT image and blood flow reserve score are synchronized into pairing, obtain source number
According to；
The corporal characteristic information of tester is added into corresponding above-mentioned source data, above-mentioned basic data is obtained.
Further, above-mentioned based in ANN blood flow reserve Score on Prediction method, above-mentioned assignment algorithm be Bayes just
Then change algorithm.
Further, above-mentioned modeling data is being passed through into finger based in ANN blood flow reserve Score on Prediction method above-mentioned
Determine algorithm to be trained before the step of obtaining blood flow reserve Score on Prediction model, further comprise the steps of:
It is respectively input layer, hidden layer and output layer that artificial neural network, which is arranged to three layers,；
The neuron number of above-mentioned input layer is adjusted identical to the input parameter type number with specified target；
6 are set by the number of the neuron of above-mentioned hidden layer.
Further, above-mentioned based in ANN blood flow reserve Score on Prediction method, by model inspection data to above-mentioned
The step of blood flow reserve Score on Prediction model is checked, including
Each layer neuron during prediction is started by Sigmoid function.
The present invention proposes a kind of based on ANN blood flow reserve Score on Prediction device, comprising:
Categorization module, for all basic datas in benchmark database to be divided into modeling data and mould according to designated ratio
Type detection data；
Modeling module obtains blood flow reserve Score on Prediction mould for above-mentioned modeling data to be trained by assignment algorithm
Type；
Module is checked, for checking by model inspection data to above-mentioned blood flow reserve Score on Prediction model；
Judgment module, for judging whether checking computation results meet specified requirement；
Prediction module, for if so, using above-mentioned blood flow reserve Score on Prediction model prediction tester blood flow reserve
Score.
The present invention proposes a kind of computer equipment, including memory, processor and storage on a memory and can located
The computer program run on reason device is realized when above-mentioned processor executes above procedure as any one of above-described embodiment is retouched
The method stated.
The present invention proposes a kind of computer readable storage medium, is stored thereon with computer program, and the program is by processor
The method as described in any one of above-described embodiment is realized when execution.
A kind of having the beneficial effect that based on ANN blood flow reserve Score on Prediction method, apparatus, equipment and medium of the invention
It can accurately predict blood flow reserve score, accuracy highest can reach 98%, and bat can reach 90% or more；Using
Range is wide, needn't know that the relationship between input parameter and reference data on formula can be predicted there is bigger freedom degree.
Detailed description of the invention
Fig. 1 is the flow diagram based on ANN blood flow reserve Score on Prediction method in one embodiment of the invention；
Fig. 2 is the flow diagram based on ANN blood flow reserve Score on Prediction method in one embodiment of the invention；
Fig. 3 is the flow diagram based on ANN blood flow reserve Score on Prediction method in one embodiment of the invention；
Fig. 4 is the flow diagram based on ANN blood flow reserve Score on Prediction method in one embodiment of the invention；
Fig. 5 is the modular structure schematic diagram based on ANN blood flow reserve Score on Prediction device in one embodiment of the invention；
Fig. 6 is a kind of structural schematic diagram of computer equipment of one embodiment of the invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiment is only a part of the embodiments of the present invention, instead of all the embodiments.Base
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts it is all its
His embodiment, shall fall within the protection scope of the present invention.
In addition, the description for being related to " first ", " second " etc. in the present invention is used for description purposes only, and should not be understood as referring to
Show or imply its relative importance or implicitly indicates the quantity of indicated technical characteristic." first ", " are defined as a result,
Two " feature can explicitly or implicitly include at least one of the features.In addition, the technical solution between each embodiment can
It to be combined with each other, but must be based on can be realized by those of ordinary skill in the art, when the combination of technical solution occurs
Conflicting or cannot achieve when, will be understood that the combination of this technical solution is not present, also not the present invention claims protection model
Within enclosing.
Referring to Fig.1, the present invention provides the present invention to propose that one kind is based on ANN blood flow reserve Score on Prediction method, including such as
Lower step:
S1, all basic datas in benchmark database are divided into modeling data and model inspection number according to designated ratio
According to；
S2, above-mentioned modeling data is trained acquisition blood flow reserve Score on Prediction model by assignment algorithm；
S3, above-mentioned blood flow reserve Score on Prediction model is checked by model inspection data；
S4, judge whether checking computation results meet specified requirement；
S5, if so, using above-mentioned blood flow reserve Score on Prediction model prediction specify target blood flow reserve score.
Such as above-mentioned steps S1, all basic datas in benchmark database are divided into modeling data and mould according to designated ratio
Type detection data, it should be noted that above-mentioned basic data generally comprise the tester of specified quantity Color Sonography image or
CT image, corporal characteristic data and blood flow reserve score, wherein corporal characteristic data include --- but being not limited to --- body
High, weight and movement velocity but other any corporal characteristic data equally can be carried out collection and as reference datas；Wherein, above-mentioned
Color Sonography image or CT image can also use B ultrasound or three-dimensional color ultrasonic image to be replaced；Wherein, above-mentioned modeling data and mould
The ratio of type detection data is preferably 70%:30%, and the method for salary distribution is randomly assigned with the quantity of tester, each builds the wooden number
According to or model inspection data include corresponding tester complete reference data.
Such as above-mentioned steps S2, above-mentioned modeling data is trained by assignment algorithm and obtains blood flow reserve Score on Prediction mould
Type；It is built it should be noted that above-mentioned modeling data generally carries out mechanics prediction training by Regularization algorithms with reaching
The purpose of vertical prediction model, but the training algorithm is not limited to Regularization algorithms further includes existing or following may be gone out
Existing other any can reach training modeling purpose algorithm.
Such as above-mentioned steps S3, above-mentioned blood flow reserve Score on Prediction model is checked by model inspection data；It uses
The corporal characteristic data of tester and the Color Sonography image or CT of tester in the model inspection data of above-mentioned steps S1 distribution
The model that image obtains above-mentioned steps S2 carries out predicted detection, by the blood flow reserve score of prediction with it is right in model inspection data
The blood flow reserve score answered compares, and obtains accuracy in detection.
Such as above-mentioned steps S4, judge whether checking computation results meet specified requirement；The detection that above-mentioned steps S3 is obtained is accurate
Degree is compared with preset value judges whether to be greater than or equal to default preset value, which is generally 90%, if judging result
Be it is no, then return to execute above-mentioned steps S2 and S3 re-establish prediction model.
Such as above-mentioned steps S5, if so, above-mentioned blood flow reserve Score on Prediction model prediction is used to specify the blood flow storage of target
Back-up number, if the judging result of above-mentioned steps S4 be it is yes, i.e., accuracy in detection be greater than or equal to 90%, then the prediction model establish
The blood flow reserve score of specified target is predicted in success using the prediction model, and wherein the biological species of the specified target must be with
The biological species of reference data in modeling process are identical, when the target organism of test or target machine type are not present when modeling
Reference data when, need to model again, this prediction technique be generally used for biology mechanics prediction, be preferred for human-body biological power
Prediction, but can also be by the modification to modeling reference data to the non-human prediction for carrying out blood flow reserve score.
Referring to Fig. 2-3, in the present embodiment, above-mentioned based in ANN blood flow reserve Score on Prediction method, by benchmark
Before the step of all basic datas in database are divided into modeling data and model inspection data according to designated ratio, further include
Step:
S6, benchmark database is established.
Such as above-mentioned steps S6, benchmark database is established, the target tested as needed chooses or phase identical as targeted species
Close certain amount reference group is to obtain the reference data that support foundation enough reaches target impact prediction model, this implementation
In example, the individual amount of reference group is preferably 100.
Wherein, the step of establishing benchmark database, comprising:
S61, obtain specified quantity tester to Color Sonography image or CT image and its corporal characteristic information；
S62, pass through above-mentioned Color Sonography image or CT image, calculate the blood flow reserve score of each tester；
S63, by the corporal characteristic information of each tester, Color Sonography image or CT image and blood flow reserve score into
The synchronous pairing of row, obtains basic data；
S64, the above-mentioned foundation data conformity by each tester obtain said reference database.
Such as above-mentioned steps S61, obtain specified quantity tester to Color Sonography image or CT image and its corporal characteristic
Information, it should be noted that tester's sex ratio is generally male: schoolgirl 1:1, quantity are generally each 100 people of men and women,
In, have coronary artery there are the ratio of the patient of stenotic lesion and healthy population be 7:3.
Such as above-mentioned steps S62, pass through above-mentioned Color Sonography image or CT image, calculate the blood flow reserve of each tester
Score, steps are as follows for calculating:
Above-mentioned Color Sonography image or CT image are split, and cardiac image is obtained by morphological operation, to upper
It states cardiac image progress histogram analysis and obtains ventricular atrial image, make the difference to obtain the heart by cardiac image and ventricular atrial image
Flesh image；
Morphological dilations are carried out to the binary image of aorta images, obtain the bianry image of full aorta, and pass through
Pixel negates to obtain full aorta complementary image, carries out region growing according to the average gray put on aorta center line, obtains
Aorta images containing coronary ostium do figure with the aorta images containing coronary ostium and full aorta complementary image
As multiplication, the image containing coronary ostium is obtained, and determines coronary ostium；
Using coronary ostium as seed point on myocardium image, coronary artery is extracted by region growing, is calculated coronal dynamic
The average gray and average variance of arteries and veins extract coronary artery tree along coronary artery direction according to coronary artery intensity profile；
Coronary artery images are subjected to binaryzation, then draw iso-surface images, obtain coronary artery three-dimensional grid image；
With numerical methods of solving continuity and Navier-Stokes equation:
Wherein,P, ρ, μ are respectively flow velocity, pressure, blood flow density, blood flow viscosity, and ▽ indicates gradient, when t indicates unit
Between, the transposition of T representing matrix；
Entrance boundary condition are as follows: Paorta- 13mm mercury column-P0, wherein P0Zero stream pressure of position；
The calculating of resistance to flow output boundary condition are as follows:
Wherein, QtotalIt is myocardial volume multiplied by myocardial blood flow density, (Qoutlet)iFor the blood flow for exporting i, DiFor outlet i's
Diameter, (Routlet)iFor the assistant for exporting i, coronary flow reserve CFR is set as 2.7；
Calculate the pressure (P of each point in three-dimensional networkoutlet)i, and it is calculated by the following formula blood flow reserve score FFR；
Wherein, PaortaIt is AoMP, (Poutlet)iIt is the pressure value of three-dimensional grid image midpoint i.
Such as above-mentioned steps S63, by the corporal characteristic information of each tester, Color Sonography image or CT image and blood flow
Deposit score synchronizes pairing, obtains basic data, which includes a tester in Color Sonography image or CT
Image and the blood flow reserve score under the image state.
Such as above-mentioned steps S64, the above-mentioned foundation data conformity by each tester under corresponding states, said reference is obtained
Database retells all tests by the foundation data conformity under each tester's different conditions at a corresponding data list
The data list of person carries out integration and obtains said reference database.
Referring to Fig. 4, in the present embodiment, above-mentioned based in ANN blood flow reserve Score on Prediction method, by each test
The corporal characteristic information of person and blood flow reserve score, acceleration and angular speed under corresponding active state synchronize and match
It is right, obtain basic data the step of, comprising:
S641, the above-mentioned cardiac image of each tester and ventricular atrial image filtering are handled；
S642, the Color Sonography image of each tester or CT image and blood flow reserve score are synchronized into pairing, obtained
Obtain source data；
S643, the corporal characteristic information of tester is added into corresponding above-mentioned source data, obtains above-mentioned basic data.
It handles, passes through such as above-mentioned steps S641, by the above-mentioned cardiac image of each tester and ventricular atrial image filtering
Specified function is filtered processing to above-mentioned data, it should be noted that above-mentioned filtration step be generally combined high-pass filter,
Low-pass filter and Butterworth filter are filtered processing to above-mentioned data.
It is carried out such as above-mentioned steps S642, by the Color Sonography image of each tester or CT image and blood flow reserve score same
Step pairing, obtains source data, the corresponding heart after searching tester corresponding with above-mentioned blood flow reserve score and filtration treatment
Color ultrasonic image or CT image, and integrated, obtain source data；
It adds such as above-mentioned steps S643, by the corporal characteristic information of tester into corresponding above-mentioned source data, in acquisition
State basic data.
In the present embodiment, above-mentioned based in ANN blood flow reserve Score on Prediction method, above-mentioned assignment algorithm is pattra leaves
This regularization algorithm, Regularization algorithms improve its Generalization Ability by correcting the training performance function of neural network,
It is realized in Matlab environment using trainbr training function.Under normal circumstances, the training performance function of neural network uses
Mean square error mse, i.e.,
In formula: mse is mean square error；N is sample number；Ti is desired output；Ai is network reality output.
In Regularization algorithms, network performance function is improved to become following form:
Msereg=γ mse+ (1- γ) msw (2)
In formula: msereg is improved error function；γ is proportionality coefficient；Msw is network ownership value quadratic sum
Average value,Wi is connection weight, the same formula of other parameters (1).
From formula (2), Regularization algorithms not only can guarantee that network training error is as small as possible, and make network
Effective weight it is as few as possible, this is effectively equivalent to the scale for reducing network automatically, and the chance that over training occurs will
Very little.The size of γ can be adaptively adjusted in Regularization algorithms in network training process, and reaches optimal.
--- but being not limited to --- Scaled Conjugate Gradient Method or LM algorithm it should be noted that above-mentioned assignment algorithm further includes
(Levenberg Marquardt, LMA).
It above-mentioned based in ANN blood flow reserve Score on Prediction method, is built in the present embodiment by above-mentioned referring to Fig. 2
Modulus is further comprised the steps of: according to before being trained the step of obtaining blood flow reserve Score on Prediction model by assignment algorithm
S7, artificial neural network is arranged to three layers of respectively input layer, hidden layer and output layer；
S8, the neuron number of above-mentioned input layer is adjusted it is identical to the input parameter type number with specified target；
S9,6 are set by the number of the neuron of above-mentioned hidden layer.
ANN refers to the complex network structures for being interconnected by a large amount of processing unit (artificial neuron) and being formed, and is pair
Certain of human brain tissue structure and operating mechanism are abstract, simplify and simulate.Artificial neural network (Artificial Neural
Network, abbreviation ANN), with the activity of mathematical model imictron, be based on imitating cerebral nerve network structure and function and
A kind of information processing system established.
Artificial neural network is divided into multilayer and single layer, and each layer includes several neurons, can with band between each neuron
The directed arc of variable weight connects, and network changes neuron company by the repetition learning training to Given information, by gradually adjusting
The method for connecing weight achievees the purpose that handle relationship between information, simulation input output.It is required no knowledge about between input and output
Definite relationship, be not required to quantity of parameters, it is only necessary to know the non-constant factor for causing output to change, i.e. non-constant parameter.Cause
This is compared with traditional data processing method, and nerual network technique is in processing fuzzy data, random data, nonlinear data side
Mask has a clear superiority, big to scale, structure is complicated, the indefinite system of information is especially suitable.It is mentioned by Minsley and Papert
Multi-layer feedforward neural networks (also referred to as multilayer perceptron) out are presently the most common network structure.
Being arranged to three layers such as above-mentioned steps S7, by artificial neural network is respectively input layer, hidden layer and output layer, is needed
Illustrate, the even number of plies of artificial neural network includes three layers of --- but being not limited to ---, can be according to existing situation to the people
The adjustment of the artificial neural networks progress number of plies.
It adjusts such as above-mentioned steps S8, by the neuron number of above-mentioned input layer to the input parameter species number with specified target
Mesh is identical, and by adjusting only the neuronal quantity of above-mentioned input layer, parameter type number is identical makes each input parameter with input
Type becomes correlated variables, makes prediction with accurate, wherein input parameter type generally with the data class phase in reference data
Together.
6 are set as such as above-mentioned steps S9, by the number of the neuron of above-mentioned hidden layer, it should be noted that although
6 are set by the neuron number of above-mentioned hidden layer in the present embodiment, the neuron number that can be called in hidden layer should be managed
Solution is that can be adjusted the neuronal quantity of hidden layer calling to reach optimum efficiency greater than 6, and according to the actual situation.
In the present embodiment, pass through model inspection data pair based in ANN blood flow reserve Score on Prediction method above-mentioned
The step of above-mentioned blood flow reserve Score on Prediction model is checked, including
Each layer neuron during prediction is started by Sigmoid function.
If above-mentioned steps start each layer neuron during prediction by Sigmoid function, Sigmoid function
It is a common S type function in biology, also referred to as S sigmoid growth curve.In information science, due to its list increasing and instead
Function list properties, the Sigmoid function such as increases and is often used as the threshold function table of neural network, by variable mappings to 0, between 1.
It carries out it should be noted that above-mentioned steps S31 generally passes through Sigmoid function to each layer nerve during prediction
Member is started, but the run function is not limited to Sigmoid function, further include it is existing or the future may appear other are any
Can reach starting purpose function, such as: ReLu (ReCTified Linear Units) run function, TanH function and
ArCTan function.
Referring to Fig. 5, the present invention proposes a kind of based on ANN blood flow reserve Score on Prediction device, comprising:
Categorization module 1, for by all basic datas in benchmark database according to designated ratio be divided into modeling data and
Model inspection data；
Modeling module 2 obtains blood flow reserve Score on Prediction for above-mentioned modeling data to be trained by assignment algorithm
Model；
Module 3 is checked, for checking by model inspection data to above-mentioned blood flow reserve Score on Prediction model；
Judgment module 4, for judging whether checking computation results meet specified requirement；
Prediction module 5, for if so, using above-mentioned blood flow reserve Score on Prediction model prediction tester blood flow reserve
Score.
Above-mentioned categorization module 1 is generally used for for all basic datas in benchmark database being divided into according to designated ratio and build
Modulus evidence and model inspection data, it should be noted that above-mentioned basic data generally comprises the heart of the tester of specified quantity
Color ultrasonic image or CT image, corporal characteristic data and blood flow reserve score, wherein corporal characteristic data include --- but it is unlimited
In --- height, weight and movement velocity but other any corporal characteristic data equally can be carried out collection and as reference datas；
Wherein, above-mentioned Color Sonography image or CT image can also use B ultrasound or three-dimensional color ultrasonic image to be replaced；Wherein, above-mentioned to build
Modulus is preferably 70%:30% according to the ratio with model inspection data, and the method for salary distribution is randomly assigned with the quantity of tester,
Each builds the wooden data or model inspection data include the complete reference data of corresponding tester.
Above-mentioned modeling module 2 is generally used for above-mentioned modeling data being trained acquisition blood flow reserve by assignment algorithm
Score on Prediction model；It should be noted that above-mentioned modeling data generally carries out mechanics prediction instruction by Regularization algorithms
Practice to achieve the purpose that establish prediction model, but the training algorithm is not limited to Regularization algorithms, further include it is existing or
The future may appear other it is any can reach training modeling purpose algorithm.
Above-mentioned checking computations module 3 is generally used for carrying out above-mentioned blood flow reserve Score on Prediction model by model inspection data
Checking computations；The corporal characteristic data of tester and the Color Sonography of tester in the model inspection data distributed using above-mentioned steps S1
Image or CT image carry out predicted detection to the model that above-mentioned steps S2 is obtained, by the blood flow reserve score and model inspection of prediction
Corresponding blood flow reserve score compares in data, obtains accuracy in detection.
Above-mentioned judgment module 4 is generally used for judging whether checking computation results meet specified requirement；Above-mentioned checking computations module 3 is obtained
Accuracy in detection out is compared with preset value judges whether to be greater than or equal to default preset value, which is generally
90%, if judging result be it is no, return to and above-mentioned modeling module 2 and checking computations module 3 called to re-establish prediction model.
Above-mentioned prediction module 5 is generally used for if so, specifying target using above-mentioned blood flow reserve Score on Prediction model prediction
Biological blood flow reserve score, if the judging result of above-mentioned judgment module 4 be it is yes, i.e., accuracy in detection be greater than or equal to 90%,
Then the prediction model is successfully established, and the biological blood flow reserve score of specified target is predicted using the prediction model, wherein this is specified
The biological species of target must be identical as the biological species of the reference data in modeling process, when the target organism or target of test
It when reference data when modeling is not present in kinds of machine, needs to model again, the mechanics that this prediction technique is generally used for biology is pre-
It surveys, is preferred for the prediction of body biomechanics, but can also be by the modification to modeling reference data to non-human carry out blood flow
Lay in the prediction of score.
Referring to Fig. 6, in embodiments of the present invention, the present invention also provides a kind of computer equipment, above-mentioned computer equipment 12
It is showed in the form of universal computing device, the component of computer equipment 12 can include but is not limited to: one or more processing
Device or processing unit 16, system storage 28 connect different system components (including system storage 28 and processing unit 16)
Bus 18.
Bus 18 indicates one of a few 18 structures of class bus or a variety of, including memory bus 18 or memory control
Device, peripheral bus 18, graphics acceleration port, processor or the office using 18 structure of any bus in a variety of 18 structures of bus
Domain bus 18.For example, these architectures include but is not limited to industry standard architecture (ISA) bus 18, microchannel
Architecture (MAC) bus 18, enhanced isa bus 18, audio-video frequency electronic standard association (VESA) local bus 18 and outer
Enclose component interconnection (PCI) bus 18.
Computer equipment 12 typically comprises a variety of computer system readable media.These media can be it is any can be by
The usable medium that computer equipment 12 accesses, including volatile and non-volatile media, moveable and immovable medium.
System storage 28 may include the computer system readable media of form of volatile memory, such as arbitrary access
Memory (RAM) 30 and/or cache memory 32.Computer equipment 12 may further include other movement/it is not removable
Dynamic, volatile/non-volatile computer decorum storage medium.Only as an example, storage system 34 can be used for read and write can not
Mobile, non-volatile magnetic media (commonly referred to as " hard disk drive ").Although being not shown in Fig. 6, can provide for can
The disc driver of mobile non-volatile magnetic disk (such as " floppy disk ") read-write, and to removable anonvolatile optical disk (such as CD~
ROM, DVD~ROM or other optical mediums) read-write CD drive.In these cases, each driver can pass through one
A or multiple data mediums interface is connected with bus 18.Memory may include at least one program product, the program product
With one group of (for example, at least one) program module 42, these program modules 42 are configured to perform the function of various embodiments of the present invention
Energy.
Program/utility 40 with one group of (at least one) program module 42, can store in memory, for example,
Such program module 42 includes --- but being not limited to --- operating system, one or more application program, other program moulds
It may include the realization of network environment in block 42 and program data, each of these examples or certain combination.Program mould
Block 42 usually executes function and/or method in embodiment described in the invention.
Computer equipment 12 can also with one or more external equipments 14 (such as keyboard, sensing equipment, display 24,
Camera etc.) communication, the equipment interacted with the computer equipment 12 can be also enabled a user to one or more to be communicated, and/
Or with enable the computer equipment 12 and one or more other calculate any equipment that equipment are communicated (such as network interface card,
Modem etc.) communication.This communication can be carried out by interface input/output (I/O) 22.Also, computer equipment
12 can also by network adapter 20 and one or more network (such as local area network (LAN)), wide area network (WAN) and/or
Public network (such as internet) communication.As shown, network adapter 20 passes through other of bus 18 and computer equipment 12
Module communication.It should be understood that although being not shown in Fig. 6 other hardware and/or software mould can be used in conjunction with computer equipment 12
Block, including but not limited to: microcode, device driver, redundant processing unit 16, external disk drive array, RAID system, magnetic
Tape drive and data backup storage system 34 etc..
Processing unit 16 by the program that is stored in system storage 28 of operation, thereby executing various function application and
Data processing, such as realize and be based on ANN blood flow reserve Score on Prediction method provided by the embodiment of the present invention.
That is, above-mentioned processing unit 16 is realized when executing above procedure: all basic datas in benchmark database are pressed
It is divided into modeling data and model inspection data according to designated ratio；Above-mentioned modeling data is trained acquisition blood by assignment algorithm
Stream deposit Score on Prediction model；Above-mentioned blood flow reserve Score on Prediction model is checked by model inspection data；Judgement is tested
Calculate whether result meets specified requirement；If so, specifying the blood flow of target using above-mentioned blood flow reserve Score on Prediction model prediction
Lay in score.
In embodiments of the present invention, the present invention also provides a kind of computer readable storage medium, it is stored thereon with computer
Program is realized when the program is executed by processor if all embodiments offers of the application are based on ANN blood flow reserve Score on Prediction
Method:
That is, realization when being executed by processor to program: by all basic datas in benchmark database according to specified ratio
Example is divided into modeling data and model inspection data；Above-mentioned modeling data is trained by assignment algorithm and obtains blood flow reserve point
Number prediction model；Above-mentioned blood flow reserve Score on Prediction model is checked by model inspection data；Judging checking computation results is
It is no to meet specified requirement；If so, specifying the blood flow reserve score of target using above-mentioned blood flow reserve Score on Prediction model prediction.
It can be using any combination of one or more computer-readable media.Computer-readable medium can be calculating
Machine gram signal media or computer readable storage medium.Computer readable storage medium for example can be --- but it is unlimited
In system, device or the device of --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, or any above combination.Computer
The more specific example (non exhaustive list) of readable storage medium storing program for executing includes: electrical connection with one or more conducting wires, portable
Formula computer disk, hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory
(EPOM or flash memory), optical fiber, portable compact disc read-only memory (CD~ROM), light storage device, magnetic memory device or
Above-mentioned any appropriate combination.In this document, computer readable storage medium can be it is any include or storage program
Tangible medium, the program can be commanded execution system, device or device use or in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including --- but
It is not limited to --- electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be
Any computer-readable medium other than computer readable storage medium, change computer-readable medium can send, propagate or
Transmission is for by the use of instruction execution system, device or device or program in connection.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof
Program code, above procedure design language include object oriented program language --- such as Java, Smalltalk, C+
+, further include conventional procedural programming language --- such as " C " language or similar programming language.Program code
It can fully execute on the user computer, partly execute, held as an independent software package on the user computer
Part executes on the remote computer or holds on a remote computer or server completely on the user computer for row, part
Row.In situations involving remote computers, remote computer can pass through the network of any kind --- including local area network
(LAN) or wide area network (WAN) --- it is connected to subscriber computer, or, it may be connected to outer computer (such as using because of spy
Service provider is netted to connect by internet).
A kind of beneficial effect based on ANN blood flow reserve Score on Prediction method, apparatus, equipment and storage medium of the invention
Are as follows: it can accurately predict blood flow reserve score, accuracy highest can reach 98%, and bat can reach 90% or more；
Have a wide range of application, needn't know that the relationship between input parameter and reference data on formula can be predicted, have it is bigger from
By spending.
The above description is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all utilizations
Equivalent structure or equivalent flow shift made by description of the invention and accompanying drawing content is applied directly or indirectly in other correlations
Technical field, be included within the scope of the present invention.
Claims (10)
1. one kind is based on ANN blood flow reserve Score on Prediction method, which comprises the steps of:
All basic datas in benchmark database are divided into modeling data and model inspection data according to designated ratio；
The modeling data is trained by assignment algorithm and obtains blood flow reserve Score on Prediction model；
The blood flow reserve Score on Prediction model is checked by model inspection data；
Judge whether checking computation results meet specified requirement；
If so, using the blood flow reserve score of the blood flow reserve Score on Prediction model prediction tester.
2. according to claim 1 be based on ANN blood flow reserve Score on Prediction method, which is characterized in that by reference data
It further include step before the step of all basic datas in library are divided into modeling data and model inspection data according to designated ratio
It is rapid:
Benchmark database is established,
Wherein, the step of establishing benchmark database, comprising:
Obtain specified quantity tester to Color Sonography image or CT image and its corporal characteristic information；
By the Color Sonography image or CT image, the blood flow reserve score of each tester is calculated；
The corporal characteristic information of each tester, Color Sonography image or CT image and blood flow reserve score are synchronized and matched
It is right, obtain basic data；
By the foundation data conformity of each tester, the benchmark database is obtained.
3. according to claim 2 be based on ANN blood flow reserve Score on Prediction method, which is characterized in that described by described
Color Sonography image or CT image, the step of calculating the blood flow reserve score of each tester, comprising:
The Color Sonography image or CT image are split, and cardiac image is obtained by morphological operation, to the heart
Dirty image carries out histogram analysis and obtains ventricular atrial image, makes the difference to obtain myocardium figure by cardiac image and ventricular atrial image
Picture；
Morphological dilations are carried out to the binary image of aorta images, obtain the bianry image of full aorta, and pass through pixel
It negates to obtain full aorta complementary image, region growing is carried out according to the average gray put on aorta center line, is contained
The aorta images of coronary ostium are done image with full aorta complementary image with the aorta images containing coronary ostium and are multiplied
Method obtains the image containing coronary ostium, and determines coronary ostium；
Using coronary ostium as seed point on myocardium image, coronary artery is extracted by region growing, is calculated coronarius
Average gray and average variance extract coronary artery tree along coronary artery direction according to coronary artery intensity profile；
Coronary artery images are subjected to binaryzation, then draw iso-surface images, obtain coronary artery three-dimensional grid image；
With numerical methods of solving continuity and Navier-Stokes equation:
Wherein,P, ρ, μ are respectively flow velocity, pressure, blood flow density, blood flow viscosity, and ▽ indicates gradient, and t indicates unit time, T
The transposition of representing matrix；
Entrance boundary condition are as follows: Paorta- 13mm mercury column-P0, wherein P0Zero stream pressure of position；
The calculating of resistance to flow output boundary condition are as follows:
Wherein, QtotalIt is myocardial volume multiplied by myocardial blood flow density, (Qoutlet)iFor the blood flow for exporting i, DiFor export i diameter,
(Routlet)iFor the assistant for exporting i, coronary flow reserve CFR is set as 2.7；
Calculate the pressure (P of each point in three-dimensional networkoutlet)i, and it is calculated by the following formula blood flow reserve score FFR；
Wherein, PaortaIt is AoMP, (Poutlet)iIt is the pressure value of three-dimensional grid image midpoint i.
4. according to claim 3 be based on ANN blood flow reserve Score on Prediction method, which is characterized in that by each tester
Corporal characteristic information, Color Sonography image or CT image and blood flow reserve score synchronize pairing, obtain basic data
The step of, comprising:
The cardiac image of each tester and ventricular atrial image filtering are handled；
The Color Sonography image of each tester or CT image and blood flow reserve score are synchronized into pairing, obtain source data；
The corporal characteristic information of tester is added into the corresponding source data, the basic data is obtained.
5. according to claim 1 be based on ANN blood flow reserve Score on Prediction method, which is characterized in that the assignment algorithm
For Regularization algorithms.
6. according to claim 1 be based on ANN blood flow reserve Score on Prediction method, which is characterized in that by the modeling
Before data are trained the step of obtaining blood flow reserve Score on Prediction model by assignment algorithm, further comprise the steps of:
It is respectively input layer, hidden layer and output layer that artificial neural network, which is arranged to three layers,；
The neuron number of the input layer is adjusted identical to the input parameter type number with specified target；
6 are set by the number of the neuron of the hidden layer.
7. according to claim 6 be based on ANN blood flow reserve Score on Prediction method, which is characterized in that pass through model inspection
The step of data check the blood flow reserve Score on Prediction model, including
Each layer neuron during prediction is started by Sigmoid function.
8. one kind is based on ANN blood flow reserve Score on Prediction device characterized by comprising
Categorization module, for all basic datas in benchmark database to be divided into modeling data and model inspection according to designated ratio
Measured data；
Modeling module obtains blood flow reserve Score on Prediction model for the modeling data to be trained by assignment algorithm；
Module is checked, for checking by model inspection data to the blood flow reserve Score on Prediction model；
Judgment module, for judging whether checking computation results meet specified requirement；
Prediction module, for if so, specifying the biological blood flow of target to store up using the blood flow reserve Score on Prediction model prediction
Back-up number.
9. a kind of computer equipment, can run on a memory and on a processor including memory, processor and storage
Computer program, which is characterized in that the processor is realized when executing described program such as any one of claim 1~7 institute
The method stated.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
The method as described in any one of claim 1~7 is realized when execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811333927.1A CN109326354A (en) | 2018-11-09 | 2018-11-09 | Based on ANN blood flow reserve Score on Prediction method, apparatus, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811333927.1A CN109326354A (en) | 2018-11-09 | 2018-11-09 | Based on ANN blood flow reserve Score on Prediction method, apparatus, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109326354A true CN109326354A (en) | 2019-02-12 |
Family
ID=65261311
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811333927.1A Pending CN109326354A (en) | 2018-11-09 | 2018-11-09 | Based on ANN blood flow reserve Score on Prediction method, apparatus, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109326354A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110136810A (en) * | 2019-06-12 | 2019-08-16 | 上海移视网络科技有限公司 | The analysis method of myocardial ischemia Coronary Blood Flow Reserve |
| CN110706770A (en) * | 2019-09-30 | 2020-01-17 | 上海杏脉信息科技有限公司 | Cardiac data processing apparatus, cardiac data processing method, and computer-readable storage medium |
| CN111754522A (en) * | 2020-06-19 | 2020-10-09 | 上海杏脉信息科技有限公司 | Method and device for acquiring coronary artery hemodynamic data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105608004A (en) * | 2015-12-17 | 2016-05-25 | 云南大学 | CS-ANN-based software failure prediction method |
| CN106023202A (en) * | 2016-05-20 | 2016-10-12 | 苏州润心医疗科技有限公司 | Coronary artery fractional flow reserve calculation method based on heart CT image |
| CN106456078A (en) * | 2013-10-17 | 2017-02-22 | 西门子保健有限责任公司 | Method and system for machine learning based assessment of fractional flow reserve |
| CN108451540A (en) * | 2017-02-17 | 2018-08-28 | 深圳先进技术研究院 | A kind of blood flow reserve fraction measurement method and apparatus |
-
2018
- 2018-11-09 CN CN201811333927.1A patent/CN109326354A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106456078A (en) * | 2013-10-17 | 2017-02-22 | 西门子保健有限责任公司 | Method and system for machine learning based assessment of fractional flow reserve |
| CN105608004A (en) * | 2015-12-17 | 2016-05-25 | 云南大学 | CS-ANN-based software failure prediction method |
| CN106023202A (en) * | 2016-05-20 | 2016-10-12 | 苏州润心医疗科技有限公司 | Coronary artery fractional flow reserve calculation method based on heart CT image |
| CN108451540A (en) * | 2017-02-17 | 2018-08-28 | 深圳先进技术研究院 | A kind of blood flow reserve fraction measurement method and apparatus |
Non-Patent Citations (1)
| Title |
|---|
| KASSIMU JUMAA等: "Lung Cancer Detection and Analysis Using Data Mining Techniques, Principal Component Analysis and", 《AMERICAN SCIENTIFIC RESEARCH JOURNAL FOR ENGINEERING, TECHNOLOGY, AND SCIENCES(ASRJETS)》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110136810A (en) * | 2019-06-12 | 2019-08-16 | 上海移视网络科技有限公司 | The analysis method of myocardial ischemia Coronary Blood Flow Reserve |
| CN110136810B (en) * | 2019-06-12 | 2023-04-07 | 上海移视网络科技有限公司 | Analysis method of myocardial ischemia coronary blood flow reserve |
| CN110706770A (en) * | 2019-09-30 | 2020-01-17 | 上海杏脉信息科技有限公司 | Cardiac data processing apparatus, cardiac data processing method, and computer-readable storage medium |
| CN111754522A (en) * | 2020-06-19 | 2020-10-09 | 上海杏脉信息科技有限公司 | Method and device for acquiring coronary artery hemodynamic data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105380598B (en) | Method and system for the automatic treatment planning for arteriarctia | |
| CN104736046B (en) | System and method for number evaluation vascular system | |
| CN105249954B (en) | The method and system of Hemodynamics index after prediction stenting | |
| JP6945204B2 (en) | Non-invasive methods and systems for measuring myocardial ischemia, identifying stenosis, locating, and estimating blood flow reserve ratio | |
| CN106456078B (en) | Method and system for the assessment based on machine learning to blood flow reserve score | |
| CN108511075B (en) | Method and system for non-invasively acquiring fractional flow reserve | |
| JP2018196742A (en) | System and method for determining characteristics of blood flow using flow ratio | |
| CN108665449B (en) | Deep learning model and device for predicting blood flow characteristics on blood flow vector path | |
| KR20150122183A (en) | Method and system for determining treatments by modifying patient-specific geometrical models | |
| CN109326354A (en) | Based on ANN blood flow reserve Score on Prediction method, apparatus, equipment and medium | |
| CN109036551A (en) | A kind of coronary artery physiologic index relationship is established and application method, device | |
| CN109524119B (en) | GAN-based fractional flow reserve prediction method, device, equipment and medium | |
| Luzhnov et al. | Analyzing rheoophthalmic signals in glaucoma by nonlinear dynamics methods | |
| Zhu et al. | Artificial intelligence-based echocardiographic left atrial volume measurement with pulmonary vein comparison | |
| WO2020083390A1 (en) | Method, device and system for acquiring blood flow of large artery on heart surface, and storage medium | |
| US20210290076A1 (en) | System and a method for determining a significance of a stenosis | |
| CN111297388B (en) | Fractional flow reserve measuring device | |
| CN114864095A (en) | Analysis method for blood circulation change of narrow coronary artery under combination of multiple exercise strengths | |
| CN110494893A (en) | The interaction of non-invasive imaging is monitored based on FFR | |
| US20240032847A1 (en) | Cardiac diagnostic method, non-transitory computer-readable medium and system | |
| CN117064413A (en) | Method for noninvasively calculating fractional flow reserve based on pulmonary circulation model | |
| CN113397511B (en) | Blood pressure measuring method and device | |
| Podgorsak et al. | Investigation of the accuracy of classifying coronary artery disease severity using machine learning with subdomain analysis of fractional flow reserve diagnosis in patients | |
| Serhatlıoğlu et al. | Analyses of a cirrhotic patient’s evolution using self organizing mapping and Child-Pugh scoring | |
| KR20230133021A (en) | Optimization system and method of AI algorithm for prediction coronary artery lesions based on FFR |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190212 |
|
| RJ01 | Rejection of invention patent application after publication |