CN114864095A - Analysis method for blood circulation change of narrow coronary artery under combination of multiple exercise strengths - Google Patents
Analysis method for blood circulation change of narrow coronary artery under combination of multiple exercise strengths Download PDFInfo
- Publication number
- CN114864095A CN114864095A CN202210491604.5A CN202210491604A CN114864095A CN 114864095 A CN114864095 A CN 114864095A CN 202210491604 A CN202210491604 A CN 202210491604A CN 114864095 A CN114864095 A CN 114864095A
- Authority
- CN
- China
- Prior art keywords
- image
- coronary artery
- wavelet
- stenosis
- coronary
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 38
- 230000017531 blood circulation Effects 0.000 title claims abstract description 26
- 230000008859 change Effects 0.000 title claims abstract description 21
- 210000004351 coronary vessel Anatomy 0.000 title claims description 69
- 238000000034 method Methods 0.000 claims abstract description 51
- 208000029078 coronary artery disease Diseases 0.000 claims abstract description 19
- 206010011089 Coronary artery stenosis Diseases 0.000 claims abstract description 16
- 206010003211 Arteriosclerosis coronary artery Diseases 0.000 claims abstract description 15
- 208000026758 coronary atherosclerosis Diseases 0.000 claims abstract description 15
- 230000000004 hemodynamic effect Effects 0.000 claims abstract description 15
- 238000000605 extraction Methods 0.000 claims abstract description 13
- 230000000284 resting effect Effects 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 12
- 201000000057 Coronary Stenosis Diseases 0.000 claims abstract description 10
- 230000002708 enhancing effect Effects 0.000 claims abstract description 10
- 238000012360 testing method Methods 0.000 claims abstract description 10
- 238000010586 diagram Methods 0.000 claims abstract description 9
- 230000000747 cardiac effect Effects 0.000 claims abstract description 8
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 8
- 238000013135 deep learning Methods 0.000 claims abstract description 5
- 238000002591 computed tomography Methods 0.000 claims description 51
- 208000031481 Pathologic Constriction Diseases 0.000 claims description 29
- 230000036262 stenosis Effects 0.000 claims description 29
- 208000037804 stenosis Diseases 0.000 claims description 29
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 22
- 229910052760 oxygen Inorganic materials 0.000 claims description 22
- 239000001301 oxygen Substances 0.000 claims description 22
- 210000004369 blood Anatomy 0.000 claims description 16
- 239000008280 blood Substances 0.000 claims description 16
- 210000004204 blood vessel Anatomy 0.000 claims description 15
- 230000006870 function Effects 0.000 claims description 11
- 201000010099 disease Diseases 0.000 claims description 10
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 10
- 238000004088 simulation Methods 0.000 claims description 9
- 239000012530 fluid Substances 0.000 claims description 8
- 230000008901 benefit Effects 0.000 claims description 6
- 238000000354 decomposition reaction Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 210000000709 aorta Anatomy 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 230000036772 blood pressure Effects 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 3
- 239000000463 material Substances 0.000 claims description 3
- 230000036284 oxygen consumption Effects 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 238000009877 rendering Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000010008 shearing Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 208000027418 Wounds and injury Diseases 0.000 abstract description 2
- 230000006378 damage Effects 0.000 abstract description 2
- 208000014674 injury Diseases 0.000 abstract description 2
- 238000001356 surgical procedure Methods 0.000 abstract description 2
- 238000003745 diagnosis Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 208000024172 Cardiovascular disease Diseases 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 238000001727 in vivo Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000037081 physical activity Effects 0.000 description 2
- 230000001629 suppression Effects 0.000 description 2
- 206010003210 Arteriosclerosis Diseases 0.000 description 1
- 201000001320 Atherosclerosis Diseases 0.000 description 1
- 208000037260 Atherosclerotic Plaque Diseases 0.000 description 1
- 210000001367 artery Anatomy 0.000 description 1
- 230000036770 blood supply Effects 0.000 description 1
- 230000002612 cardiopulmonary effect Effects 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000008021 deposition Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 230000037213 diet Effects 0.000 description 1
- 235000005911 diet Nutrition 0.000 description 1
- 230000002526 effect on cardiovascular system Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000004217 heart function Effects 0.000 description 1
- 238000000338 in vitro Methods 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 230000004199 lung function Effects 0.000 description 1
- 230000002107 myocardial effect Effects 0.000 description 1
- 210000004165 myocardium Anatomy 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000037074 physically active Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
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
- G16H50/50—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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20064—Wavelet transform [DWT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20132—Image cropping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
- G06T2207/30104—Vascular flow; Blood flow; Perfusion
Abstract
The invention discloses an analysis method for coronary artery stenosis blood circulation change under the combination of multiple exercise strengths, which comprises the steps of firstly constructing an image sample library for a coronary artery stenosis CT image, and carrying out label type processing; denoising and enhancing a CT original sequence diagram extracted from the cardiac CTA by adopting a wavelet correlation method; performing feature extraction on the CT image by adopting a convolutional neural network model CNN in a deep learning method, segmenting by adopting an Otsu method, and finally performing three-dimensional reconstruction; carrying out finite element analysis on the three-dimensional reconstructed image; and finally, testing the wall shear force, the blood flow speed, the wall pressure and the wall deformation change of the patient in the resting state and under the conditions of different movement strengths. The invention measures the hemodynamic analysis of the patient with coronary atherosclerosis under the resting and three different levels of exercise intensity, realizes the accurate judgment on the control of the state of an illness, and avoids the injury to the patient caused by invasive surgery.
Description
Technical Field
The invention belongs to the technical field of bioengineering, and particularly relates to an analysis method for blood circulation change of a narrow coronary artery under the condition of combining multiple exercise strengths.
Background
Coronary heart disease, one of the diseases seriously endangering human life, is mainly caused by coronary artery lumen stenosis caused by coronary atherosclerosis, and the over-narrowed blood vessel can block blood circulation, so that the myocardial blood supply is insufficient, and a series of clinical symptoms are finally caused. The coronary artery is a blood vessel which specially supplies blood to the heart and the cardiac muscle, and is very important for human body, and is shaped like a cap which is buckled on the heart, the initial end of the cap is connected with the main blood vessel of the aorta, and a plurality of branch blood vessels are extended like a trunk, and the blood vessels surround the whole heart and are attached on the heart. Over time, deposits form on the walls of the coronary vessels, which are medically known as arterial plaque or atheroma. Coronary atherosclerosis refers to this phenomenon of arterial deposition. Patients suffering from atherosclerosis have a high blood viscosity and contain clots, which, under their combined influence, can block arteries, thereby making blood unavailable and interrupting flow.
There is a great deal of evidence that the greater the amount of physical activity in everyday practice, the better the cardiopulmonary function, and the lower the incidence and mortality of cardiovascular disease, both of which are inversely related. For example, the cardiovascular risk of the people with the largest activity or the best heart and lung function is respectively reduced by 30 percent and 64 percent in normal times; the life expectancy of the most physically active person is 7-8 years at age 50. Furthermore, the benefits of exercise are not limited to healthy people, and regular physical activity by patients with cardiovascular disease also helps to reduce relapse and improve survival. The coronary artery stenosis is irreversible, and can effectively control the state of an illness and prevent deterioration through reasonable exercise and diet.
Disclosure of Invention
The invention aims to provide an analysis method for blood circulation change of a narrow coronary artery under the combination of multiple exercise strengths, which measures the hemodynamic analysis of a coronary atherosclerosis patient under the resting and three different levels of exercise strengths, realizes accurate judgment on the control of the disease condition and avoids the injury to the patient caused by invasive surgery.
The technical scheme adopted by the invention is that the analysis method for the blood circulation change of the narrow coronary artery under the condition of combining multiple exercise strengths is implemented according to the following steps:
step 1, constructing an image sample library for a coronary artery stenosis CT image, and performing label classification processing;
step 2, denoising and enhancing pretreatment are carried out on the CT original sequence diagram extracted from the cardiac CTA in the step 1 by adopting a wavelet correlation method;
step 3, extracting features of the CT image by adopting a convolutional neural network model CNN in a deep learning method, segmenting by adopting an Otsu method, and finally performing three-dimensional reconstruction;
step 4, according to 7: 3, dividing the M grouped samples into a training group and a testing group by adopting a random index method, and carrying out finite element analysis on the three-dimensional reconstructed image in the step 3;
and 5, uniformly concentrating the patients screened in the step 4, and ensuring that the wall shear force, the blood flow speed, the wall pressure and the wall deformation change conditions of the patients are tested under the conditions of rest state and different movement strengths of the patients under all normal conditions.
The present invention is also characterized in that,
the step 1 is implemented according to the following steps:
collecting information and images of patients who have undergone cardiac CTA and DSA examinations in a hospital data system in the last year, namely, enabling CT images and coronary stenosis index data to correspond to each other, hiding basic information of the patients in the images, labeling the types of labels, screening 400 cases of patients with the age of 20-50 and the stenosis range of 25% -49% according to the image quality, and taking coronary CT images under rest and different intensity exercise grades as selected input samples, wherein the exercise intensity grade is divided into five grades according to the maximum oxygen consumption VO2max, and the first grade is as follows: the maximum oxygen uptake is less than 45%; and (2) second stage: the maximum oxygen uptake is 55-65%; third-stage: the maximum oxygen uptake is 75-85%; and (4) fourth stage: the maximum oxygen uptake is 90-95%; and (5) fifth stage: the maximum oxygen uptake is greater than 95%.
The step 2 is implemented according to the following steps:
step 2.1, firstly, carrying out image denoising treatment, carrying out normalization treatment on the selected input sample in the step 1, wherein the size of a unified picture is 512 x 512, carrying out wavelet decomposition on an original signal and a noise-containing signal in the sample by adopting a Mallat algorithm to obtain a multilayer low-frequency signal wavelet coefficient and a multilayer detail signal wavelet coefficient, then carrying out denoising treatment by adopting a wavelet local threshold method, and finally carrying out wavelet reconstruction to obtain a sample of a denoised signal;
the method for using the wavelet local threshold specifically comprises the following steps:
the threshold values are selected as follows:
taking in the diagonal direction:
wherein λ is 1 A threshold value in the diagonal direction is adopted, sigma is the standard deviation of noise, and N is the scale or the length of a signal;
taking in the horizontal H and vertical V directions:
wherein λ is 2 The threshold values in the horizontal H direction and the vertical V direction are provided, sigma is the standard deviation of noise, and N is the scale or the length of a signal;
σ is estimated as:
wherein M represents the absolute value of the median of the wavelet coefficients of the detail signal of the layer 1 of the wavelet transform;
selecting a threshold function:
the threshold function is a rule for modifying wavelet coefficients, and is:
wherein, w j 、 k Is a two-dimensional wavelet coefficient with a threshold value of λ 1 、λ 2 ;
Step 2.2, performing enhancement processing on the de-noised image, adopting a wavelet image sub-band enhancement algorithm, performing 2-layer wavelet decomposition in the first step, and respectively extracting wavelet coefficients of a low-frequency sub-image and a low-frequency sub-image; secondly, determining a high-frequency wavelet threshold; thirdly, calculating the gain coefficient of each layer; and fourthly, denoising and enhancing the wavelet coefficients of the low-frequency sub-image and the high-frequency sub-image by multiplying different weights according to the requirement of image enhancement to process the wavelet coefficients.
Step 2.2 in the wavelet image subband enhancement algorithm, the enhancement weight of the low-frequency subimage isThe high-frequency subimages are processed by adopting a formula:
selecting the threshold value l of image enhancement as 0.1, the enhancement coefficient k of vertical edge subgraph HL and horizontal edge subgraph LH as 20, the enhancement coefficient k of diagonal subgraph HH as 23, and finally performing wavelet inverse transformation on the enhanced wavelet coefficient to obtain the enhanced image.
The step 3 is as follows:
step 3.1, extracting the characteristics of the coronary artery through a convolution-pooling layer and generating a characteristic diagram of the coronary artery on the CT image obtained after denoising and enhancing in the step 2; then after a feature map is generated, extracting a candidate region of a suspected coronary artery by using a candidate region network RPN, wherein the feature extraction and the candidate frame extraction of the image are in shared convolution, and the feature extraction network of the image uses a residual error network of 50-layer convolution to extract a coronary artery gray region map;
step 3.2, the coronary artery gray area image extracted in the step 3.1 is segmented and extracted by adopting an improved Otsu algorithm, a threshold value T is selected, pixels of the image are traversed, pixels with the gray values smaller than T are divided into backgrounds, pixels with the gray values larger than T are divided into target areas, normalization processing is carried out on the gray image to be segmented, and a threshold value selection criterion function is improved as follows:
wherein σ ω (t) represents the intra-class variance with exponential parameter, μ B (t) and μ o (t) mean values of the Intra-class grays representing the background and object, p i Representing the probability of different gray levels, t representing time, and i representing different values of gray values;
calculating a connected region of the segmented image; counting pixel points which are considered to be coronary arteries and fall into each communication area; selecting the region where the counting value is the largest and judging the region as the coronary artery, and removing the region with the small counting value, thereby completing the segmentation and extraction of the coronary artery region;
3.3, performing three-dimensional reconstruction on coronary artery blood vessels by adopting a ray projection method in volume rendering on the image segmented in the step 3.2, and performing three-dimensional reconstruction on coronary arteries including the aorta to finally obtain a three-dimensional reconstructed coronary artery model;
and 3.4, importing the coronary artery model after three-dimensional reconstruction in the step 3.3 into Geomagicstudio12.0 software, correcting small holes or gaps in the model to obtain a blood vessel model with a smooth surface, cutting the model, only reserving the right coronary artery, finally fitting the curved surface to automatically generate a NURBS curved surface, and storing and exporting the right coronary artery three-dimensional model into an IGS format file.
The step 4 is as follows:
step 4.1, introducing the right coronary artery three-dimensional model in the step 3 into ANSYS workbench18.0 software, performing surface setting and boundary layer setting on a blood and blood vessel wall model by adopting a hexahedral mesh in an ICEM CFD module in the ANSYS software, then performing mesh division, controlling the mesh size of the blood vessel wall to be 0.1-0.5 mm, controlling the mesh size of the blood model to be 0.4-5 mm, performing local encryption on the blood model, setting a solver, next, introducing the model set in the ICEM CFD module into a CFX module in the ANSYS software, performing fluid parameter and boundary parameter setting, then performing finite element iterative computation for 100 times, and finally obtaining a CFD model;
and 4.2, performing hemodynamic numerical simulation on the CFD model in the ANSYS software in the step 4.1, and analyzing the four aspects of blood flow velocity, wall surface pressure, wall surface shearing force and wall surface deformation according to a numerical simulation result to obtain the hemodynamic characteristics of the patient with the right coronary artery stenosis rate of 26-50% in a resting state.
Finite element iterative computation in the step 4.1 depends on three fundamental equations of hydrodynamics, namely a continuous equation, a Naiver-Stokes equation and an energy equation, which are respectively as follows:
wherein in the formulae (7) to (9), ρ is the density of blood, u is a blood flow velocity vector,denotes the material derivative, μ is the hemodynamic viscosity, p is the blood pressure,is the Laplace operator, Q is the increase of the heat of the fluid in unit volume, e is the internal energy of the fluid in unit mass, Q i Is the vector component of heat.
The step 5 is as follows:
step 5.1, selecting a patient with a right coronary artery stenosis rate of 25% -49% as a sample, classifying the sample into three categories according to age, and classifying the sample into a group A according to 20-29 years old; grouping B at age of 30-39 years old; grouping C at age of 40-50 years old;
step 5.2, centralizing the patients of the group A, the group B and the group C in the step 5.1, enabling the established laboratory to be close to a CT (computed tomography) room, and sequentially entering the laboratory to measure and calculate different exercise intensities: firstly, moving to a CT room to shoot a resting state CT image; step 1, when the instrument displays that the maximum oxygen uptake reaches 35%, namely the first-level exercise intensity, the instrument stops exercising and immediately goes to a CT room to shoot a CT image, and similarly, when the oxygen uptake reaches 55% and 75%, namely the second-level and third-level exercise intensities, the instrument goes to the CT room to shoot the CT image in sequence;
step 5.3, performing all the operations from the step 2 to the step 4 on the CT images of the patients in different stages in the step 5.2 to finally obtain the hemodynamic numerical simulation analysis result of the right coronary artery of the patients under three different intensity movements;
and 5.4, summarizing all numerical analysis results of the samples, comparing the analysis result of the right coronary artery stenosis part of the patient in a resting state with the analysis result of the right coronary artery stenosis part of the patient in different exercise intensity levels, researching the advantages and disadvantages of the exercise intensity on patients with coronary artery II-level stenosis, and obtaining an exercise strategy for reasonably controlling the disease condition of the patients with coronary atherosclerosis in the first-level exercise intensity, the second-level exercise intensity and the third-level exercise intensity in the step 5.2.
The method has the advantages that the method combines the analysis method of the blood circulation change of the narrow coronary artery under the multi-movement intensity, can correspond the CT and DSA images and the diagnosis report of the existing patient, can compare the four index change conditions of the coronary atherosclerosis patient under the movement of different intensities by directly using the cardiac CT detection result and utilizing the hydromechanics finite element analysis, and further determines the movement intensity scheme for reasonably controlling the state of an illness. The invention adopts an in vitro test and in vivo analysis and prediction mode, reasonably plans the influence of the exercise intensity on the disease control, prevents the serious condition of the patient from coronary atherosclerosis to coronary heart disease in advance, has good performance in prediction speed, lightens the psychological burden of the patient, makes a reasonable disease control strategy and improves the diagnosis efficiency of a clinician.
Drawings
FIG. 1 is a schematic diagram of a framework of the present invention based on kinematic strength and finite element analysis models;
FIG. 2 is a block diagram of sample classification according to the present invention;
FIG. 3 is a flow chart of wavelet image subband enhancement algorithm of the present invention;
FIG. 4 is a coronary artery identification network of the present invention;
FIG. 5 is a flow chart of numerical analysis of the present invention.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
The invention provides an analysis method combining the blood movement change of a narrow coronary artery under multiple movement strengths based on the original intention of reasonably controlling the disease condition of a coronary atherosclerosis patient, and compares the change conditions of four indexes of the coronary atherosclerosis patient under different movement strengths by utilizing finite element analysis to further determine a movement scheme. Referring to fig. 1, an overall frame diagram, the method mainly includes six basic modules, namely, building a sample library, preprocessing an image, extracting features, segmenting, reconstructing three dimensions, and performing finite element analysis in hydrodynamics, and can be understood as mainly including two main stages, namely, sample acquisition and classification and finite element analysis. In the stage of sample acquisition and classification, as shown in fig. 2, various processing procedures on the training samples need to be completed, and in the stage of finite element analysis, numerical models of the same sample in different states need to be analyzed and compared, so that the most effective exercise intensity for the patient is obtained. It should be noted that the present invention is directed to the present protocol but not limited thereto, and is applicable to the diagnosis of other diseases besides being suitable for the study setting.
The invention relates to a method for analyzing blood circulation change of a narrow coronary artery under the condition of combining multiple exercise strengths, which is implemented by the following steps as shown in a flow chart shown in figure 1:
step 1, constructing an image sample library for a coronary stenosis CT image, and performing label type processing;
with reference to fig. 2, step 1 is specifically performed according to the following steps:
collecting information and images of patients who have undergone cardiac CTA and DSA examinations in a hospital data system in the last year, namely, enabling CT images and coronary stenosis index data to correspond to each other, hiding basic information of the patients in the images, labeling the types of labels, screening 400 cases of patients with the age of 20-50 and the stenosis range of 25% -49% according to the image quality, and taking coronary CT images under rest and different intensity exercise grades as selected input samples, wherein the exercise intensity grade is divided into five grades according to the maximum oxygen consumption VO2max, and the first grade is as follows: the maximum oxygen uptake is less than 45%; and (2) second stage: the maximum oxygen uptake is 55-65%; third-stage: the maximum oxygen uptake is 75-85%; and (4) fourth stage: the maximum oxygen uptake is 90-95%; and (5) fifth stage: the maximum oxygen uptake is greater than 95%.
Step 2, denoising and enhancing pretreatment are carried out on the CT original sequence diagram extracted from the cardiac CTA in the step 1 by adopting a wavelet correlation method;
the step 2 is implemented according to the following steps:
step 2.1, in medical images, the suppression of noise is a particularly elaborate and complex task. The detail features are important basis for the doctor to analyze the problem and diagnose whether the organ has lesion, so the important features of the original image must be kept as much as possible while suppressing the noise when the medical image is denoised. The wavelet transform has good time-frequency localization capability and multi-resolution analysis capability, so that the locality regularity of image signals can be characterized, and the noise suppression and image enhancement algorithm of the wavelet analyzed medical image is applied, so that the detail characteristics of the image are not lost as much as possible when the image noise is suppressed, and the noise is not amplified when the image is enhanced.
Firstly, carrying out image denoising treatment, carrying out normalization treatment on the input sample selected in the step 1, wherein the size of a picture is unified into 512 x 512, carrying out wavelet decomposition on an original signal and a noise-containing signal in the sample by adopting a Mallat algorithm to obtain a multilayer low-frequency signal wavelet coefficient and a multilayer detail signal wavelet coefficient, then carrying out denoising treatment by adopting a wavelet local threshold method, and finally carrying out wavelet reconstruction to obtain a sample of a denoised signal;
the method for using the wavelet local threshold specifically comprises the following steps:
the threshold values are selected as follows:
taking in the diagonal direction:
wherein λ is 1 A threshold value in the diagonal direction is adopted, sigma is the standard deviation of noise, and N is the scale or the length of a signal;
taking in the horizontal H and vertical V directions:
wherein λ is 2 The threshold values in the horizontal H direction and the vertical V direction are provided, sigma is the standard deviation of noise, and N is the scale or the length of a signal;
since the noise level is unknown, σ is estimated as:
wherein M represents the absolute value of the median of the wavelet coefficients of the detail signal of the layer 1 of the wavelet transform;
the wavelet coefficient larger than the threshold is considered to be generated by signals and should be reserved, and the wavelet coefficient smaller than the threshold is considered to be generated by noise and is set to be zero, so that the purpose of denoising is achieved.
Selecting a threshold function:
the local characteristics such as image edges and the like can be well reserved by the threshold method, but visual distortion such as ringing, pseudo Gibbs effect and the like can occur in the image, while the processing result of the soft threshold method is relatively smooth, but the soft threshold method can cause distortion phenomena such as edge blurring and the like. Aiming at the point, a soft and hard threshold compromise method is adopted, a threshold function is a rule for modifying wavelet coefficients, and the threshold function is as follows:
wherein w j 、 k Is a two-dimensional wavelet coefficient with a threshold value of λ 1 、λ 2 ;
The image quality of the CT image can be improved through the denoising processing in the step 2.1, and meanwhile, the denoised image can more clearly embody the coronary artery structure information in the CT image, and the image enhancement operation in the step 2.2 is facilitated to be promoted.
With reference to fig. 3, step 2.2, in order to improve the resolution and facilitate the subsequent segmentation of the image, the denoised image is enhanced, a wavelet image subband enhancement algorithm is adopted, and the first step is to perform 2-layer wavelet decomposition and extract wavelet coefficients of a low-frequency sub-image and a low-frequency sub-image respectively; secondly, determining a high-frequency wavelet threshold (a proper threshold can effectively suppress noise and enhance edges); thirdly, calculating the gain coefficient of each layer; and fourthly, denoising and enhancing the wavelet coefficients of the low-frequency sub-image and the high-frequency sub-image by multiplying different weights according to the requirement of image enhancement to process the wavelet coefficients.
Step 2.2 is the wavelet image subband enhancement algorithm, the flow chart is shown in FIG. 3, and the enhancement weight of the low-frequency subimage isThe high-frequency subimages are processed by adopting a formula:
selecting a threshold l of image enhancement to be 0.1 according to the characteristics of the image, selecting an enhancement coefficient k of a vertical edge sub-image HL and a horizontal edge sub-image LH to be 20, and an enhancement coefficient k of a diagonal sub-image HH to be 23, and finally performing wavelet inverse transformation on the enhanced wavelet coefficient to obtain the enhanced image.
Step 3, extracting features of the CT image by adopting a convolutional neural network model CNN in a deep learning method, segmenting by adopting an Otsu method, and finally performing three-dimensional reconstruction;
the step 3 is as follows:
step 3.1, extracting the features of the coronary artery through a convolution-pooling layer and generating a feature map of the coronary artery for the CT image obtained after denoising and enhancing in the step 2 as shown in a coronary artery identification network of FIG. 4; then after a feature map is generated, a candidate region of a suspected coronary artery is extracted by using a candidate region network RPN, the feature extraction and the candidate frame extraction of the image are in shared convolution, and a residual error network of 50-layer convolution is used by a feature extraction network of the image, so that a gray region map of the coronary artery can be extracted;
step 3.2, the coronary artery gray area image extracted in the step 3.1 is segmented and extracted by adopting an improved Otsu algorithm, a threshold value T is selected, pixels of the image are traversed, pixels with the gray values smaller than T are divided into backgrounds, pixels with the gray values larger than T are divided into target areas, normalization processing is carried out on the gray image to be segmented, and a threshold value selection criterion function is improved as follows:
wherein σ ω (t) represents the intra-class variance with exponential parameter, μ B (t) and μ o (t) mean values of the Intra-class grays representing the background and object, p i Representing the probability of different gray levels, t representing time, and i representing different values of gray values;
calculating a connected region of the segmented image; counting pixel points which are considered to be coronary arteries and fall into each communication area; selecting the region where the counting value is the largest and judging the region as the coronary artery, and removing the region with the small counting value, thereby completing the segmentation and extraction of the coronary artery region;
3.3, performing three-dimensional reconstruction on coronary artery blood vessels by adopting a ray projection method in volume rendering on the image segmented in the step 3.2, and performing three-dimensional reconstruction on coronary arteries including the aorta to finally obtain a three-dimensional reconstructed coronary artery model;
and 3.4, importing the coronary artery model after three-dimensional reconstruction in the step 3.3 into Geomagicstudio12.0 software, correcting small holes or gaps in the model to obtain a blood vessel model with a smooth surface, cutting the model, only reserving the right coronary artery, finally fitting the curved surface to automatically generate a NURBS curved surface, and storing and exporting the right coronary artery three-dimensional model into an IGS format file.
Step 4, according to 7: 3, dividing the M grouped samples into a training group and a testing group by adopting a random index method, and carrying out finite element analysis on the three-dimensional reconstructed image in the step 3;
the step 4 is as follows:
step 4.1, as shown in the flow chart of fig. 5, introducing the right coronary artery three-dimensional model in the step 3 into ANSYS Workbench18.0 software, performing surface setting and boundary layer setting on a blood and blood vessel wall model by adopting a hexahedral mesh in an ICEM CFD module in the ANSYS software, then performing mesh division, controlling the mesh size of the blood vessel wall to be 0.1-0.5 mm, controlling the mesh size of the blood model to be within the range of 0.4-5 mm, performing local encryption on the blood model, setting a solver, next, introducing the model set in the ICEM CFD module into a CFX module in the ANSYS software, performing fluid parameter and boundary parameter setting, and performing finite element iterative computation for 100 times to finally obtain a CFD model; and 4.2, four hemodynamics (CFD) indexes are conveniently analyzed.
And 4.2, performing hemodynamic numerical simulation on the CFD model in the ANSYS software in the step 4.1, and analyzing the four aspects of blood flow velocity, wall surface pressure, wall surface shearing force and wall surface deformation according to a numerical simulation result to obtain the hemodynamic characteristics of the patient with the right coronary artery stenosis rate of 26-50% in a resting state. This facilitates comparative analysis of the final study results in step 5.
Finite element iterative computation in the step 4.1 depends on three fundamental equations of hydrodynamics, namely a continuous equation, a Naiver-Stokes equation and an energy equation, which are respectively as follows:
wherein in the formulae (7) to (9), ρ is the density of blood, u is a blood flow velocity vector,denotes the material derivative, μ is the hemodynamic viscosity, p is the blood pressure,is the Laplace operator, Q is the increase of the heat of the fluid in unit volume, e is the internal energy of the fluid in unit mass, Q i Is the vector component of heat.
And 5, uniformly concentrating the patients screened in the step 4, and ensuring that the wall shear force, the blood flow speed, the wall pressure and the wall deformation change conditions of the patients are tested under the conditions of rest state and different movement strengths of the patients under all normal conditions.
The step 5 is as follows:
and 5.1, selecting a patient with a right coronary artery stenosis rate of 25-49% as a sample, wherein the patient with the stenosis rate is in a critical range of coronary atherosclerosis and coronary heart disease, and the patient with the lower stenosis rate and the patient with the higher stenosis rate, which are not obvious and have high risk in the experiment, is reduced, so that the stenosis rate range is selected as the sample.
Table 1 SCCT rating scale for degree of stenosis
Degree of stenosis of lumen diameter | Term(s) for |
0% | Without stenosis |
1%~24% | Very small stenosis |
25%~49% | Mild stenosis |
50%~69% | Moderate stenosis |
70%~99% | Severe stenosis |
100% | Occlusion |
Firstly, classifying the age of a sample into three groups, wherein the sample is classified into a group A after 20-29 years old; grouping B at age of 30-39 years old; grouping C at age of 40-50 years old; A. b, C three groups of samples of different ages to reduce errors due to age.
Step 5.2, centralizing the patients of the group A, the group B and the group C in the step 5.1, enabling the established laboratory to be close to a CT (computed tomography) room, and sequentially entering the laboratory to measure and calculate different exercise intensities: firstly, moving to a CT room to shoot a resting state CT image; step 1, when the instrument displays that the maximum oxygen uptake reaches 35%, namely the first-level exercise intensity, the instrument stops exercising and immediately goes to a CT room to shoot a CT image, and similarly, when the oxygen uptake reaches 55% and 75%, namely the second-level and third-level exercise intensities, the instrument goes to the CT room to shoot the CT image in sequence; since the measurement ranges of the sub-maximum strength and the maximum strength (fourth-order strength and fifth-order strength) are not included in consideration of the physical load bearing capacity of the patient, the resting state and the first, second and third levels are evaluated in the laboratory.
Step 5.3, performing all the operations from the step 2 to the step 4 on the CT images of the patients in different stages in the step 5.2 to finally obtain the hemodynamic numerical simulation analysis result of the right coronary artery of the patients under three different intensity movements;
and 5.4, summarizing all numerical analysis results of the samples, comparing the analysis results of the right coronary artery stenosis part of the patient in a resting state with the analysis results of the right coronary artery stenosis part of the patient in different exercise intensity levels, researching the advantages and disadvantages of the exercise intensity on patients with coronary artery II-level stenosis, and finding out an exercise strategy for reasonably controlling the disease condition of patients with coronary atherosclerosis.
Step 5.2 the laboratory requirements are as follows:
a) keeping the temperature at 19-21 ℃;
b) relative humidity is 40-60%;
c) the indoor air must be kept fresh;
d) the indoor oxygen content should be kept at 20.90%.
Notes tested in step 5.2:
a) before testing, an operator must know the whole operation procedure test process together with a subject, and explain the requirements on the subject and the time and process of movement;
b) the operator has to discuss the gesture communication in the operation process with the subject in advance, and if the subject has an emergency, the test is stopped immediately;
c) the subject should not participate in weight exertion activities prior to testing;
d) within one hour prior to the test, the subject was not able to smoke and eat;
e) depending on the power used by the instrument, the subject will need to select the appropriate clothing and shoes to develop the maximum level of exercise.
The invention is based on the concept of sports medicine, combines the sports with the medicine, and carries out hydromechanical finite element analysis aiming at the characteristics of the medical coronary CT image on the basis of wavelet and deep learning. The specific method comprises the following steps: the coronary vessels are segmented by the CT image to carry out modeling and numerical analysis, and the in-vivo change condition of the narrow vessels when the patient is at rest and moves with different intensities is directly diagnosed. Aiming at the coronary atherosclerosis patients with the right coronary stenosis rate of 25-49%, the patient with the stenosis rate is in the critical range of coronary atherosclerosis and coronary heart disease, so the method has higher research value, and reduces the risk of the patient with the lower stenosis rate and the patient with the high stenosis rate which is not obvious in the measurement result. According to the numerical analysis results obtained by the exercises with different levels of intensity, the advantages and disadvantages of patients with coronary artery II-level stenosis due to different exercise intensities are explored, and an exercise method for reasonably controlling the disease condition of patients with coronary atherosclerosis is found out.
Claims (8)
1. A method for analyzing blood circulation change of a narrow coronary artery under the condition of combining multiple exercise strengths is characterized by comprising the following steps:
step 1, constructing an image sample library for a coronary stenosis CT image, and performing label type processing;
step 2, denoising and enhancing the CT original sequence diagram extracted from the cardiac CTA in the step 1 by adopting a wavelet correlation method;
step 3, extracting features of the CT image by adopting a convolutional neural network model CNN in a deep learning method, segmenting by adopting an Otsu method, and finally performing three-dimensional reconstruction;
step 4, according to 7: 3, dividing the M grouped samples into a training group and a testing group by adopting a random index method, and carrying out finite element analysis on the three-dimensional reconstructed image in the step 3;
and 5, uniformly concentrating the patients screened in the step 4, and ensuring that the wall shear force, the blood flow speed, the wall pressure and the wall deformation change conditions of the patients are tested under the conditions of rest state and different movement strengths of the patients under all normal conditions.
2. The method for analyzing stenosis coronary blood circulation change under multiple exercise intensities according to claim 1, wherein the step 1 is specifically performed according to the following steps:
collecting information and images of patients who have undergone cardiac CTA and DSA examinations in a hospital data system in the last year, namely, enabling CT images and coronary stenosis index data to correspond to each other, hiding basic information of the patients in the images, labeling the types of labels, screening 400 cases of patients with the age of 20-50 and the stenosis range of 25% -49% according to the image quality, and taking coronary CT images under rest and different intensity exercise grades as selected input samples, wherein the exercise intensity grade is divided into five grades according to the maximum oxygen consumption VO2max, and the first grade is as follows: the maximum oxygen uptake is less than 45%; and (2) second stage: the maximum oxygen uptake is 55-65%; third-stage: the maximum oxygen uptake is 75-85%; and (4) fourth stage: the maximum oxygen uptake is 90-95%; and (5) fifth stage: the maximum oxygen uptake is greater than 95%.
3. The method for analyzing stenosis coronary blood circulation change under multiple exercise intensities according to claim 2, wherein the step 2 is implemented according to the following steps:
step 2.1, firstly, carrying out image denoising treatment, carrying out normalization treatment on the selected input sample in the step 1, wherein the size of a unified picture is 512 x 512, carrying out wavelet decomposition on an original signal and a noise-containing signal in the sample by adopting a Mallat algorithm to obtain a multilayer low-frequency signal wavelet coefficient and a multilayer detail signal wavelet coefficient, then carrying out denoising treatment by adopting a wavelet local threshold method, and finally carrying out wavelet reconstruction to obtain a sample of a denoised signal;
the method for using the wavelet local threshold specifically comprises the following steps:
the threshold values are selected as follows:
taking in the diagonal direction:
wherein λ is 1 A threshold value in the diagonal direction is adopted, sigma is the standard deviation of noise, and N is the scale or the length of a signal;
taking in the horizontal H and vertical V directions:
wherein λ is 2 The threshold values in the horizontal H direction and the vertical V direction are provided, sigma is the standard deviation of noise, and N is the scale or the length of a signal;
σ is estimated as:
wherein M represents the absolute value of the median of the wavelet coefficients of the detail signal of the layer 1 of the wavelet transform;
selecting a threshold function:
the threshold function is a rule for modifying wavelet coefficients, and is:
wherein, w j 、 k Is a two-dimensional wavelet coefficient with a threshold value of λ 1 、λ 2 ;
Step 2.2, performing enhancement processing on the de-noised image, adopting a wavelet image sub-band enhancement algorithm, performing 2-layer wavelet decomposition in the first step, and respectively extracting wavelet coefficients of a low-frequency sub-image and a low-frequency sub-image; secondly, determining a high-frequency wavelet threshold; thirdly, calculating the gain coefficient of each layer; and fourthly, denoising and enhancing the wavelet coefficients of the low-frequency sub-image and the high-frequency sub-image by multiplying different weights according to the requirement of image enhancement to process the wavelet coefficients.
4. The method for analyzing the blood vessel movement change of the coronary artery with stenosis under the combination of multiple exercise intensities as claimed in claim 3, wherein in the wavelet image sub-band enhancement algorithm in the step 2.2, the enhancement weight of the low frequency sub-image isThe high-frequency subimages are processed by adopting a formula:
selecting the threshold value l of image enhancement as 0.1, the enhancement coefficient k of vertical edge subgraph HL and horizontal edge subgraph LH as 20, the enhancement coefficient k of diagonal subgraph HH as 23, and finally performing wavelet inverse transformation on the enhanced wavelet coefficient to obtain the enhanced image.
5. The method for analyzing stenosis coronary blood circulation variation under multiple exercise intensity according to claim 4, wherein the step 3 is as follows:
step 3.1, extracting the characteristics of the coronary artery through a convolution-pooling layer and generating a characteristic diagram of the coronary artery on the CT image obtained after denoising and enhancing in the step 2; then after a feature map is generated, extracting a candidate region of a suspected coronary artery by using a candidate region network RPN, wherein the feature extraction and the candidate frame extraction of the image are in shared convolution, and the feature extraction network of the image uses a residual error network of 50-layer convolution to extract a coronary artery gray region map;
step 3.2, the coronary artery gray area image extracted in the step 3.1 is segmented and extracted by adopting an improved Otsu algorithm, a threshold value T is selected, pixels of the image are traversed, pixels with the gray values smaller than T are divided into backgrounds, pixels with the gray values larger than T are divided into target areas, normalization processing is carried out on the gray image to be segmented, and a threshold value selection criterion function is improved as follows:
wherein σ ω (t) represents the within-class variance with exponential parameter, μ B (t) and μ o (t) mean values of the Intra-class grays representing the background and object, p i Representing the probability of different gray levels, t representing time, and i representing different values of gray values;
calculating a connected region of the segmented image; counting pixel points which are considered to be coronary arteries and fall into each communication area; selecting the region where the counting value is the largest and judging the region as the coronary artery, and removing the region with the small counting value, thereby completing the segmentation and extraction of the coronary artery region;
3.3, performing three-dimensional reconstruction on coronary artery blood vessels by adopting a ray projection method in volume rendering on the image segmented in the step 3.2, and performing three-dimensional reconstruction on coronary arteries including the aorta to finally obtain a three-dimensional reconstructed coronary artery model;
and 3.4, importing the coronary artery model after three-dimensional reconstruction in the step 3.3 into Geomagicstudio12.0 software, correcting small holes or gaps in the model to obtain a blood vessel model with a smooth surface, cutting the model, only reserving the right coronary artery, finally fitting the curved surface to automatically generate a NURBS curved surface, and storing and exporting the right coronary artery three-dimensional model into an IGS format file.
6. The method for analyzing stenosis coronary blood circulation variation under multiple exercise intensity according to claim 5, wherein the step 4 comprises the following steps:
step 4.1, introducing the right coronary artery three-dimensional model in the step 3 into ANSYS Workbench18.0 software, performing surface setting and boundary layer setting on a blood and blood vessel wall model by adopting a hexahedral mesh in an ICEM CFD module in the ANSYS software, then performing mesh division, controlling the mesh size of the blood vessel wall to be 0.1-0.5 mm, controlling the mesh size of the blood model to be 0.4-5 mm, performing local encryption on the blood model, setting a solver, next, introducing the model set in the ICEM CFD module into a CFX module in the ANSYS software, performing fluid parameter and boundary parameter setting, then performing finite element iterative computation for 100 times, and finally obtaining a CFD model;
and 4.2, performing hemodynamic numerical simulation on the CFD model in the ANSYS software in the step 4.1, and analyzing the four aspects of blood flow velocity, wall surface pressure, wall surface shearing force and wall surface deformation according to a numerical simulation result to obtain the hemodynamic characteristics of the patient with the right coronary artery stenosis rate of 26-50% in a resting state.
7. The method for analyzing stenosis coronary blood circulation change under multiple exercise intensities according to claim 6, wherein finite element iterative computation in the step 4.1 depends on three basic equations of hydrodynamics, namely a continuity equation, a Naiver-Stokes equation and an energy equation, which are respectively as follows:
wherein in the formulae (7) to (9), ρ is the density of blood, u is a blood flow velocity vector,denotes the material derivative, μ is the hemodynamic viscosity, p is the blood pressure,is Laplace operator, Q is a unit volume of fluidIncrease in heat quantity, e is the internal energy per unit mass of fluid, q i Is the vector component of heat.
8. The method for analyzing stenosis coronary blood circulation variation under multiple exercise intensity according to claim 7, wherein the step 5 comprises the following steps:
step 5.1, selecting patients with the right coronary artery stenosis rate of 25% -49% as samples, classifying the samples into three categories according to age, and classifying the samples into A group according to the age of 20-29 years; grouping B at age of 30-39 years old; grouping C at age of 40-50 years old;
step 5.2, centralizing the patients of the group A, the group B and the group C in the step 5.1, enabling the established laboratory to be close to a CT (computed tomography) room, and sequentially entering the laboratory to measure and calculate different exercise intensities: firstly, moving to a CT room to shoot a resting state CT image; step 1, when the instrument displays that the maximum oxygen uptake reaches 35%, namely the first-level exercise intensity, the instrument stops exercising and immediately goes to a CT room to shoot a CT image, and similarly, when the oxygen uptake reaches 55% and 75%, namely the second-level and third-level exercise intensities, the instrument goes to the CT room to shoot the CT image in sequence;
step 5.3, performing all the operations from the step 2 to the step 4 on the CT images of the patients in different stages in the step 5.2 to finally obtain the hemodynamic numerical simulation analysis result of the right coronary artery of the patients under three different intensity movements;
and 5.4, summarizing all numerical analysis results of the samples, comparing the analysis result of the right coronary artery stenosis part of the patient in a resting state with the analysis result of the right coronary artery stenosis part of the patient in different exercise intensity levels, researching the advantages and disadvantages of the exercise intensity on patients with coronary artery II-level stenosis, and obtaining an exercise strategy for reasonably controlling the disease condition of the patients with coronary atherosclerosis in the first-level exercise intensity, the second-level exercise intensity and the third-level exercise intensity in the step 5.2.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210491604.5A CN114864095A (en) | 2022-04-29 | 2022-04-29 | Analysis method for blood circulation change of narrow coronary artery under combination of multiple exercise strengths |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210491604.5A CN114864095A (en) | 2022-04-29 | 2022-04-29 | Analysis method for blood circulation change of narrow coronary artery under combination of multiple exercise strengths |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114864095A true CN114864095A (en) | 2022-08-05 |
Family
ID=82634810
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210491604.5A Pending CN114864095A (en) | 2022-04-29 | 2022-04-29 | Analysis method for blood circulation change of narrow coronary artery under combination of multiple exercise strengths |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114864095A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117478432A (en) * | 2023-12-27 | 2024-01-30 | 国网天津市电力公司信息通信公司 | Safety operation and maintenance system for power communication equipment |
-
2022
- 2022-04-29 CN CN202210491604.5A patent/CN114864095A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117478432A (en) * | 2023-12-27 | 2024-01-30 | 国网天津市电力公司信息通信公司 | Safety operation and maintenance system for power communication equipment |
CN117478432B (en) * | 2023-12-27 | 2024-03-19 | 国网天津市电力公司信息通信公司 | Safety operation and maintenance system for power communication equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Su et al. | Lung nodule detection based on faster R-CNN framework | |
Saikumar et al. | A novel implementation heart diagnosis system based on random forest machine learning technique. | |
CN105279759B (en) | The abdominal cavity aortic aneurysm outline dividing method constrained with reference to context information arrowband | |
JP2019018032A (en) | Systems and methods for image-based object modeling using multiple image acquisitions or reconstructions | |
KR101902883B1 (en) | A method for analyzing plaque in a computed tomography image and an apparatus thereof | |
CN108577883A (en) | A kind of Screening for coronary artery disease device, screening system and signal characteristic extracting methods | |
Liu et al. | Automatic whole heart segmentation using a two-stage u-net framework and an adaptive threshold window | |
JP2007502676A (en) | Automated method and system for vascular plaque detection and analysis | |
CN113420826B (en) | Liver focus image processing system and image processing method | |
CN110946619B (en) | Intravascular ultrasound automatic image histology analysis system and analysis method | |
Cao et al. | Deep learning methods for cardiovascular image | |
US20210027461A1 (en) | Systems and methods for determining a fluid and tissue volume estimations using electrical property tomography | |
CN110558960A (en) | continuous blood pressure non-invasive monitoring method based on PTT and MIV-GA-SVR | |
CN113935976A (en) | Method and system for automatically segmenting blood vessels in internal organs by enhancing CT (computed tomography) image | |
Revathi et al. | An intelligent model for coronary heart disease diagnosis | |
CN114864095A (en) | Analysis method for blood circulation change of narrow coronary artery under combination of multiple exercise strengths | |
CN113408603A (en) | Coronary artery stenosis degree identification method based on multi-classifier fusion | |
Zhu et al. | Artificial intelligence-based echocardiographic left atrial volume measurement with pulmonary vein comparison | |
Xiao et al. | PET and CT image fusion of lung cancer with siamese pyramid fusion network | |
Niu et al. | Improving automated tissue characterization in optical coherence tomography by melding attenuation compensation with deep learning | |
Wang et al. | A myocardial segmentation method based on adversarial learning | |
Zhan et al. | Recognition of angiographic atherosclerotic plaque development based on deep learning | |
Hakim et al. | Tuberculosis detection analysis using texture features on CXRs images | |
CN117197594B (en) | Deep neural network-based heart shunt classification system | |
Zhao et al. | Intracranial vascular structure extraction: a machine learning approach |
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 |