CN114010157A - Blood vessel plaque risk prediction method, device, equipment and medium - Google Patents
Blood vessel plaque risk prediction method, device, equipment and medium Download PDFInfo
- Publication number
- CN114010157A CN114010157A CN202111296678.5A CN202111296678A CN114010157A CN 114010157 A CN114010157 A CN 114010157A CN 202111296678 A CN202111296678 A CN 202111296678A CN 114010157 A CN114010157 A CN 114010157A
- Authority
- CN
- China
- Prior art keywords
- blood vessel
- plaque
- user
- risk
- information
- 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
- 210000004204 blood vessel Anatomy 0.000 title claims abstract description 382
- 238000000034 method Methods 0.000 title claims abstract description 104
- 230000000004 hemodynamic effect Effects 0.000 claims abstract description 130
- 238000010801 machine learning Methods 0.000 claims description 59
- 238000004364 calculation method Methods 0.000 claims description 35
- 238000013058 risk prediction model Methods 0.000 claims description 33
- 230000002792 vascular Effects 0.000 claims description 33
- 238000004422 calculation algorithm Methods 0.000 claims description 24
- 238000001914 filtration Methods 0.000 claims description 19
- 239000012530 fluid Substances 0.000 claims description 19
- 238000003672 processing method Methods 0.000 claims description 14
- 230000009514 concussion Effects 0.000 claims description 10
- 230000017531 blood circulation Effects 0.000 abstract description 14
- 238000012545 processing Methods 0.000 description 22
- 238000013528 artificial neural network Methods 0.000 description 20
- 208000024172 Cardiovascular disease Diseases 0.000 description 11
- 208000026106 cerebrovascular disease Diseases 0.000 description 11
- 230000002526 effect on cardiovascular system Effects 0.000 description 11
- 230000002308 calcification Effects 0.000 description 7
- 238000002591 computed tomography Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000013398 bayesian method Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 6
- 238000010968 computed tomography angiography Methods 0.000 description 6
- 238000007637 random forest analysis Methods 0.000 description 6
- 238000012706 support-vector machine Methods 0.000 description 6
- 210000004369 blood Anatomy 0.000 description 5
- 239000008280 blood Substances 0.000 description 5
- 238000004590 computer program Methods 0.000 description 5
- 238000002595 magnetic resonance imaging Methods 0.000 description 5
- 238000004088 simulation Methods 0.000 description 5
- 210000004351 coronary vessel Anatomy 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000002608 intravascular ultrasound Methods 0.000 description 4
- 238000010606 normalization Methods 0.000 description 4
- 238000012014 optical coherence tomography Methods 0.000 description 4
- 230000009467 reduction Effects 0.000 description 4
- 238000012502 risk assessment Methods 0.000 description 4
- 230000003321 amplification Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000012804 iterative process Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000003199 nucleic acid amplification method Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 208000031481 Pathologic Constriction Diseases 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000036772 blood pressure Effects 0.000 description 2
- 239000002872 contrast media Substances 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 230000002107 myocardial effect Effects 0.000 description 2
- 208000037804 stenosis Diseases 0.000 description 2
- 230000036262 stenosis Effects 0.000 description 2
- 230000009897 systematic effect Effects 0.000 description 2
- 208000007536 Thrombosis Diseases 0.000 description 1
- 241000170489 Upis Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 210000000601 blood cell Anatomy 0.000 description 1
- 230000036770 blood supply Effects 0.000 description 1
- 230000000747 cardiac effect Effects 0.000 description 1
- 210000000748 cardiovascular system Anatomy 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000002586 coronary angiography Methods 0.000 description 1
- 238000013434 data augmentation Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 231100000915 pathological change Toxicity 0.000 description 1
- 230000036285 pathological change Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000003325 tomography Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 238000012285 ultrasound imaging Methods 0.000 description 1
- 230000002861 ventricular Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/02007—Evaluating blood vessel condition, e.g. elasticity, compliance
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0033—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room
- A61B5/004—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room adapted for image acquisition of a particular organ or body part
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/02028—Determining haemodynamic parameters not otherwise provided for, e.g. cardiac contractility or left ventricular ejection fraction
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/026—Measuring blood flow
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/05—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves
- A61B5/055—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7271—Specific aspects of physiological measurement analysis
- A61B5/7275—Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/02—Arrangements for diagnosis sequentially in different planes; Stereoscopic radiation diagnosis
- A61B6/03—Computed tomography [CT]
- A61B6/032—Transmission computed tomography [CT]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/46—Arrangements for interfacing with the operator or the patient
- A61B6/461—Displaying means of special interest
- A61B6/466—Displaying means of special interest adapted to display 3D data
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/50—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications
- A61B6/504—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications for diagnosis of blood vessels, e.g. by angiography
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/52—Devices using data or image processing specially adapted for radiation diagnosis
- A61B6/5211—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/08—Detecting organic movements or changes, e.g. tumours, cysts, swellings
- A61B8/0891—Detecting organic movements or changes, e.g. tumours, cysts, swellings for diagnosis of blood vessels
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/5215—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- 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
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
- G06T2207/30104—Vascular flow; Blood flow; Perfusion
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- Biophysics (AREA)
- Veterinary Medicine (AREA)
- Surgery (AREA)
- Heart & Thoracic Surgery (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Radiology & Medical Imaging (AREA)
- Physiology (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- High Energy & Nuclear Physics (AREA)
- General Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Psychiatry (AREA)
- Cardiology (AREA)
- Optics & Photonics (AREA)
- Vascular Medicine (AREA)
- Data Mining & Analysis (AREA)
- Epidemiology (AREA)
- Databases & Information Systems (AREA)
- Primary Health Care (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Quality & Reliability (AREA)
- Hematology (AREA)
- Pulmonology (AREA)
- Geometry (AREA)
- Human Computer Interaction (AREA)
Abstract
The application discloses a blood vessel plaque risk prediction method, a device, equipment and a medium, which are used for acquiring an original medical image of a blood vessel of a user and generating a blood vessel model of the blood vessel of the user according to the original medical image; determining hemodynamic parameters of a blood vessel of a user according to the blood vessel model; plaque risk information of a blood vessel of a user is predicted based on hemodynamic parameters, and the plaque risk information comprises plaque growth risk and plaque rupture risk. The blood flow dynamics parameters of the blood vessels of the user can be accurately calculated through the blood vessel model generated based on the original medical images of the blood vessels of the user, plaque growth risks and plaque rupture risks of the blood vessels of the user are evaluated based on the blood flow dynamics parameters, plaque risk information of the blood vessels of the user is obtained, and plaques in the blood vessels of the user are effectively monitored according to the plaque growth and rupture conditions in the plaque risk information.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to a method, an apparatus, a device, and a medium for predicting a vascular plaque risk.
Background
Cardiovascular and cerebrovascular diseases are the most fatal diseases in China at present. Plaque growth, rupture, sloughing, etc. in the blood vessel pose a fatal risk to the patient. Currently, there is no complete and systematic risk prediction method for the whole life cycle of plaque in blood vessels, and the plaque cannot be monitored according to the growth and rupture conditions of the plaque.
Disclosure of Invention
The main purpose of the present application is to provide a blood vessel plaque risk prediction method, device, apparatus and medium, which aim to realize plaque monitoring according to the growth and rupture conditions of plaque.
In order to achieve the above object, an embodiment of the present application provides a vascular plaque risk prediction method, including:
acquiring an original medical image of a user blood vessel, and generating a blood vessel model of the user blood vessel according to the original medical image;
determining hemodynamic parameters of the user's blood vessel from the vessel model;
predicting plaque risk information for the user's blood vessel based on the hemodynamic parameters, the plaque risk information including a plaque growth risk and a plaque rupture risk.
Preferably, the step of predicting plaque risk information of the user's blood vessel based on the hemodynamic parameter comprises:
predicting plaque risk information of the blood vessel of the user according to the hemodynamic parameters and a preset prediction mode based on a plaque risk calculation formula; or
And predicting plaque risk information of the blood vessel of the user according to the hemodynamic parameters and a prediction mode of a preset plaque risk prediction model based on machine learning.
Preferably, the step of predicting plaque risk information of the user's blood vessel based on the hemodynamic parameter further comprises:
acquiring geometric information of the blood vessel of the user and/or characteristic information of plaque in the blood vessel of the user based on the original medical image;
predicting plaque risk information of the blood vessel of the user according to the geometric information and/or the characteristic information and the hemodynamic parameter.
Preferably, the step of predicting plaque risk information of the blood vessel of the user according to the geometric information and/or the characteristic information and the hemodynamic parameter comprises:
predicting plaque risk information of the blood vessel of the user according to the geometric information and/or the characteristic information and the hemodynamic parameters in combination with a preset prediction mode based on a plaque risk calculation formula; or
And predicting the plaque risk information of the blood vessel of the user according to the geometric information and/or the characteristic information and the hemodynamic parameters in combination with a prediction mode of a preset plaque risk prediction model based on machine learning.
Preferably, the step of generating a vessel model of the user's vessel from the original medical image comprises:
generating a blood vessel model of the blood vessel of the user according to a preset image processing method and the original medical image, wherein the preset image processing method comprises a threshold method and a filtering method; or
And generating a blood vessel model of the blood vessel of the user according to a blood vessel prediction algorithm based on machine learning and the original medical image.
Preferably, the step of determining hemodynamic parameters of the user's blood vessel from the vessel model comprises:
determining hemodynamic parameters of the blood vessel of the user according to the blood vessel model and a dynamic parameter prediction algorithm based on machine learning; or
And determining the hemodynamic parameters of the blood vessel of the user according to the blood vessel model and the computational fluid dynamics method.
Preferably, the hemodynamic parameter comprises one or more of wall shear, axial plaque stress, concussion shear index, time-averaged wall shear, fractional flow reserve.
To achieve the above object, the present application also provides a blood vessel plaque risk prediction device, including:
the acquisition module is used for acquiring an original medical image of a blood vessel of a user and generating a blood vessel model of the blood vessel of the user according to the original medical image;
a determining module for determining hemodynamic parameters of the user's blood vessel from the blood vessel model;
a prediction module for predicting plaque risk information of the user's blood vessel based on the hemodynamic parameter, the plaque risk information including a plaque growth risk and a plaque rupture risk.
Further, to achieve the above object, the present application also provides a blood vessel plaque risk prediction apparatus, which includes a memory, a processor, and a blood vessel plaque risk prediction program stored in the memory and executable on the processor, and when executed by the processor, implements the steps of the blood vessel plaque risk prediction method described above.
Further, to achieve the above object, the present application also provides a medium, which is a computer readable storage medium, on which a vascular plaque risk prediction program is stored, and when the vascular plaque risk prediction program is executed by a processor, the method of predicting vascular plaque risk described above is implemented.
Further, to achieve the above object, the present application also provides a computer program product comprising a computer program, which when executed by a processor, implements the steps of the vascular plaque risk prediction method described above.
The embodiment of the application provides a method, a device, equipment and a medium for predicting the risk of blood vessel plaque, which are used for acquiring an original medical image of a blood vessel of a user and generating a blood vessel model of the blood vessel of the user according to the original medical image; determining hemodynamic parameters of the user's blood vessel from the vessel model; predicting plaque risk information for the user's blood vessel based on the hemodynamic parameters, the plaque risk information including a plaque growth risk and a plaque rupture risk. The blood flow dynamics parameters of the blood vessels of the user can be accurately calculated through the blood vessel model generated based on the original medical images of the blood vessels of the user, plaque growth risks and plaque rupture risks of the blood vessels of the user are evaluated based on the blood flow dynamics parameters, plaque risk information of the blood vessels of the user is obtained, and plaques in the blood vessels of the user are effectively monitored according to the plaque growth and rupture conditions in the plaque risk information.
Drawings
Fig. 1 is a schematic structural diagram of a hardware operating environment according to an embodiment of a vascular plaque risk prediction method of the present application;
FIG. 2 is a schematic flow chart illustrating a first embodiment of a method for predicting vascular plaque risk according to the present application;
FIG. 3 is a schematic flow chart illustrating a second embodiment of a method for predicting vascular plaque risk according to the present application;
FIG. 4 is a schematic flow chart illustrating a third embodiment of a method for predicting vascular plaque risk according to the present application;
fig. 5 is a functional block diagram of a blood vessel plaque risk prediction device according to a preferred embodiment of the present invention.
The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The main solution of the embodiment of the invention is as follows: acquiring an original medical image of a user blood vessel, and generating a blood vessel model of the user blood vessel according to the original medical image; determining hemodynamic parameters of the user's blood vessel from the vessel model; predicting plaque risk information for the user's blood vessel based on the hemodynamic parameters, the plaque risk information including a plaque growth risk and a plaque rupture risk. The blood flow dynamics parameters of the blood vessels of the user can be accurately calculated through the blood vessel model generated based on the original medical images of the blood vessels of the user, plaque growth risks and plaque rupture risks of the blood vessels of the user are evaluated based on the blood flow dynamics parameters, plaque risk information of the blood vessels of the user is obtained, and plaques in the blood vessels of the user are effectively monitored according to the plaque growth and rupture conditions in the plaque risk information.
The technical terms related to the embodiment of the invention comprise:
CTA: computed tomography angiography; the method is to scan coronary arteries by using multi-row helical CT (Computed Tomography) to obtain a coronary Tomography image, so as to know the pathological changes of the coronary arteries.
Plaque: plaque refers to diseased tissue that grows out of the vascular sandwich; plaque presents many hazards to blood vessels, such as: the blood vessel lumen is compressed, and the blood supply is influenced; rupture and fall into the blood vessel to form thrombus.
Hemodynamics: refers to the mechanics of blood flow in the cardiovascular system, and is mainly used for studying blood flow, blood flow resistance, blood pressure and their interrelation. Blood is a fluid, and thus the basic principle of hemodynamics is the same as that of general hydrodynamics. However, because the vascular system is a relatively complex elastic pipeline system, and blood is liquid containing various components such as blood cells, colloidal substances and the like rather than ideal liquid, the hemodynamics not only has the common characteristics of general hydrodynamics, but also has the characteristics of the hemodynamics.
The embodiment of the application considers that the current evaluation technology for the risk of the vascular plaque is relatively few, generally focuses on the rupture risk, and almost does not evaluate the growth risk. That is, there is currently no complete and systematic plaque risk assessment method to predict the risk of the entire life cycle of plaque, including plaque growth and rupture.
Therefore, the embodiment of the invention provides a solution which can evaluate and monitor the plaque growth risk and the plaque rupture risk of the blood vessel of the user.
As shown in fig. 1, fig. 1 is a schematic structural diagram of a blood vessel plaque risk prediction device in a hardware operating environment according to an embodiment of the present application.
In the following description, suffixes such as "module", "component", or "unit" used to denote elements are used only for the convenience of description of the present application, and have no specific meaning by themselves. Thus, "module", "component" or "unit" may be used mixedly.
The blood vessel plaque risk prediction device in the embodiment of the application may be a PC, or may be a mobile terminal device such as a tablet computer or a portable computer.
As shown in fig. 1, the vascular plaque risk prediction apparatus may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration of the vascular plaque risk prediction device shown in fig. 1 does not constitute a limitation of the vascular plaque risk prediction device and may include more or fewer components than those shown, or some components in combination, or a different arrangement of components.
As shown in fig. 1, a memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a vascular plaque risk prediction program.
In the device shown in fig. 1, the network interface 1004 is mainly used for connecting to a backend server and performing data communication with the backend server; the user interface 1003 is mainly used for connecting a client (user side) and performing data communication with the client; and the processor 1001 may be configured to invoke a vascular plaque risk prediction program stored in the memory 1005 and perform the following operations:
acquiring an original medical image of a user blood vessel, and generating a blood vessel model of the user blood vessel according to the original medical image;
determining hemodynamic parameters of the user's blood vessel from the vessel model;
predicting plaque risk information for the user's blood vessel based on the hemodynamic parameters, the plaque risk information including a plaque growth risk and a plaque rupture risk.
Further, the step of predicting plaque risk information of the user's blood vessel based on the hemodynamic parameter comprises:
predicting plaque risk information of the blood vessel of the user according to the hemodynamic parameters and a preset prediction mode based on a plaque risk calculation formula; or
And predicting plaque risk information of the blood vessel of the user according to the hemodynamic parameters and a prediction mode of a preset plaque risk prediction model based on machine learning.
Further, the step of predicting plaque risk information of the user's blood vessel based on the hemodynamic parameter further comprises:
acquiring geometric information of the blood vessel of the user and/or characteristic information of plaque in the blood vessel of the user based on the original medical image;
predicting plaque risk information of the blood vessel of the user according to the geometric information and/or the characteristic information and the hemodynamic parameter.
Further, the step of predicting plaque risk information of the blood vessel of the user according to the geometric information and/or the characteristic information and the hemodynamic parameter comprises:
predicting plaque risk information of the blood vessel of the user according to the geometric information and/or the characteristic information and the hemodynamic parameters in combination with a preset prediction mode based on a plaque risk calculation formula; or
And predicting the plaque risk information of the blood vessel of the user according to the geometric information and/or the characteristic information and the hemodynamic parameters in combination with a prediction mode of a preset plaque risk prediction model based on machine learning.
Further, the step of generating a vessel model of the user's vessel from the original medical image comprises:
generating a blood vessel model of the blood vessel of the user according to a preset image processing method and the original medical image, wherein the preset image processing method comprises a threshold method and a filtering method; or
And generating a blood vessel model of the blood vessel of the user according to a blood vessel prediction algorithm based on machine learning and the original medical image.
Further, the step of determining hemodynamic parameters of the user's blood vessel from the vessel model comprises:
determining hemodynamic parameters of the blood vessel of the user according to the blood vessel model and a dynamic parameter prediction algorithm based on machine learning; or
And determining the hemodynamic parameters of the blood vessel of the user according to the blood vessel model and the computational fluid dynamics method.
Further, the hemodynamic parameter includes one or more of wall shear force, axial plaque stress, concussion shear index, time-averaged wall shear force, fractional flow reserve.
For a better understanding of the above technical solutions, exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments.
Referring to fig. 2, fig. 2 is a schematic flowchart of a blood vessel plaque risk prediction method according to a first embodiment of the present application. In this embodiment, the method for predicting vascular plaque risk includes the following steps:
step S10, acquiring an original medical image of a user blood vessel, and generating a blood vessel model of the user blood vessel according to the original medical image;
the blood vessel plaque risk prediction method is applied to a blood vessel plaque risk prediction system, the blood vessel plaque risk prediction system is used for executing the blood vessel plaque risk prediction method, the hemodynamic parameters of a blood vessel of a user can be accurately calculated through a blood vessel model generated based on an original medical image of the blood vessel of the user, the plaque growth risk and the plaque rupture risk of the blood vessel of the user are evaluated based on the hemodynamic parameters, plaque risk information of the blood vessel of the user is obtained, the plaque in the blood vessel of the user is monitored according to the growth and rupture conditions of the plaque in the plaque risk information, corresponding risk processing is carried out when needed, and the reduction of the fatality rate of cardiovascular and cerebrovascular diseases is facilitated.
Specifically, for a user with a vascular plaque risk prediction, a 2D or 3D original medical image of a blood vessel of the user is acquired, and specifically, the 2D or 3D original medical image may be a CT Angiography (CT Angiography) image or a Magnetic Resonance Imaging (MRI) image or an ICA (active Coronary Angiography) image or an IVUS (intravascular Ultrasound) image or an OCT (Optical Coherence Tomography) image, which is an original medical image of a blood vessel of the user, which is acquired by scanning the blood vessel of the user through a computed Tomography apparatus or a Magnetic Resonance apparatus or an X-ray contrast apparatus or an Ultrasound Imaging apparatus.
After a CTA image, an MRI image, an ICA image, an IVUS image or an OCT image of a user blood vessel is acquired as an original medical image, a geometric model of the user blood vessel is extracted from the original medical image through an image processing algorithm or an artificial intelligence algorithm to obtain a blood vessel model of the user blood vessel, wherein the image processing algorithm can be a threshold value method and a filtering method in the embodiment, the threshold value method is used for selecting a proper image intensity threshold value range according to the image intensity of the image, then segmenting the image according to the selected threshold value range, segmenting the image into a foreground and a background, and the foreground is an interested area, so that the foreground is used as the blood vessel model. The filtering method is to process an original image by using a filter, find the boundary of an interested area on the filtered image by curve fitting (curve fitting), segment the image into a foreground and a background, wherein the foreground is the interested area, and therefore the foreground is used as a blood vessel model. The artificial intelligence algorithm may include a conventional machine learning method and a deep learning method, the conventional machine learning method includes, but is not limited to, a random forest method, a multi-layer perceptron, a bayesian method, a support vector machine, and the like, the deep learning method includes, but is not limited to, CNN, RNN, a transform, and the like, in this embodiment, prediction may be performed according to an image by using the conventional machine learning method, and an area of interest, i.e., a foreground, corresponding to a blood vessel in an original medical image is used as a blood vessel model. The method and the device are convenient for determining the hemodynamic parameters of the blood vessel of the user according to the blood vessel model subsequently, predicting the plaque risk information of the blood vessel of the user based on the hemodynamic parameters, monitoring the blood vessel of the user according to the plaque risk information, processing the plaque risk when needed, and reducing the fatality rate of cardiovascular and cerebrovascular diseases. In this embodiment, the hemodynamic parameter includes one or more of a wall shear force, an axial plaque stress, a concussion shear index, a time-averaged wall shear force, and a fractional flow reserve. For example, the parameters may include parameters such as wall shear force, axial plaque stress, oscillational shear index, time-averaged wall shear force, and fractional flow reserve, the parameters may include parameters such as wall shear force, axial plaque stress, and oscillational shear index, and the parameters may include parameters such as time-averaged wall shear force and fractional flow reserve. In this embodiment, only the acquired coronary artery image of the patient is needed to be analyzed as the original medical image; and the coronary image can be obtained noninvasively, such as by CT, MRI, etc., and has the advantage of simple operation.
Further, the step of generating a vessel model of the user's vessel from the original medical image comprises:
step A, generating a blood vessel model of the blood vessel of the user according to a preset image processing method and the original medical image, wherein the preset image processing method comprises a threshold value method and a filtering method;
after a CTA image, an MRI image, an ICA image, an IVUS image, or an OCT image of a blood vessel of a user is acquired as an original medical image, the acquired original medical image may be processed by a preset image processing method in this embodiment to generate a blood vessel model of the blood vessel of the user, where the preset image processing method in this embodiment may be a threshold method, a filtering method, or the like. Therefore, in this embodiment, the acquired original medical image may be processed by a threshold method to generate a blood vessel model of the blood vessel of the user, specifically, a threshold range [ a, b ] corresponding to the image intensity is selected according to the image intensity of the original medical image. And further segmenting the original medical image according to the selected threshold range, and segmenting the original medical image into a foreground and a background, wherein the foreground is an interested area, and therefore the interested area, namely the foreground, corresponding to the blood vessel in the original medical image is used as a blood vessel model.
In this embodiment, the acquired original medical image may also be processed by a filtering method to generate a blood vessel model of the blood vessel of the user, specifically, the original medical image is processed by using a filter, where the filter includes but is not limited to: median filtering, mean filtering, bilateral filtering, Frangi filtering, Gaussian filtering, Laplace filtering, Sobel filtering, and the like. Further, the boundary of the region of interest is found on the filtered medical image through curve fitting (curve fitting), the medical image is segmented according to the boundary of the region of interest, the medical image is segmented into a foreground and a background, the foreground is the region of interest, and the region of interest is used as a blood vessel model.
Or step B, generating a blood vessel model of the blood vessel of the user according to a blood vessel prediction algorithm based on machine learning and the original medical image.
In this embodiment, the acquired original medical image may be processed by a machine learning-based blood vessel prediction algorithm to generate a blood vessel model of a blood vessel of a user, and specifically, the original medical image may be processed in a data normalization manner (data normalization) and a data amplification manner (data augmentation), where the data normalization is to linearly map gray values [ 0-255 ] of the original medical image to [0, 1 ]; the data amplification is to expand a data sample, namely an original medical image, by methods of translation, rotation, mirror image, brightness change, noise increase, scaling and the like, so that the accuracy and the robustness of the machine learning method are improved. Further, before processing the acquired original medical image through a blood vessel prediction algorithm based on machine learning, an initial neural network is constructed based on the current scene, and the medical image after data normalization and data amplification processing is predicted through the neural network to obtain a prediction result; comparing the predicted result with the artificial label and feeding back the result to the neural network so as to update the neural network and enable the neural network to evolve towards the direction of reducing the prediction error; by using a large amount of data (medical images), the iterative process is repeated thousands of times, and finally the prediction result is close to the artificial standard, so that the blood vessel prediction model containing the blood vessel prediction algorithm is obtained. Therefore, when the acquired original medical image is processed by the blood vessel prediction algorithm based on machine learning, the original medical image is input into the trained blood vessel prediction model, the input original medical image is predicted by the blood vessel prediction algorithm contained in the original medical image, and the predicted region of interest, namely the foreground, is used as the blood vessel model. It should be noted that, in the present embodiment, the blood vessel prediction model based on machine learning may be based on a traditional machine learning method, and the traditional machine learning method includes, but is not limited to, a random forest method, a multi-layer perceptron, a bayesian method, a support vector machine, and the like.
Step S20, determining the hemodynamic parameters of the blood vessel of the user according to the blood vessel model;
after generating the blood vessel model of the blood vessel of the user from the original medical image, the hemodynamic parameters of the blood vessel of the user can be determined through a simulation calculation method or a machine learning method, wherein the simulation calculation method in this embodiment adopts a Computational Fluid Dynamics (CFD) method, and the computational fluid dynamics is to solve a fluid mechanics equation by using a computer, simulate the flow condition of the simulation fluid, thereby obtaining the hydrodynamic parameters, such as flow velocity, pressure, and the like, of each point in the calculation domain, and then further obtaining the hemodynamic parameters. The machine learning method includes, but is not limited to, a random forest method, a multi-layer perceptron, a bayesian method, a support vector machine, etc., so that the hemodynamic parameters of the blood vessel of the user can be determined by predicting according to the blood vessel model through a traditional machine learning method. So that plaque risk information of the blood vessel of the user can be predicted based on the hemodynamic parameters subsequently, the blood vessel of the user can be monitored according to the plaque risk information, plaque risk processing can be carried out when needed, and the reduction of the fatality rate of cardiovascular and cerebrovascular diseases is facilitated.
Further, the step of determining hemodynamic parameters of the user's blood vessel from the vessel model comprises:
step C, determining the hemodynamic parameters of the blood vessel of the user according to the blood vessel model and a dynamic parameter prediction algorithm based on machine learning;
after a three-dimensional model of a user blood vessel is obtained by generating a blood vessel model of the user blood vessel according to an original medical image, predicting the blood vessel model by a dynamic parameter prediction algorithm based on machine learning, predicting blood flow dynamic parameters such as wall shear force (WSS) of the user blood vessel, Axial Plaque Stress (APS), Oscillational Shear Index (OSI), time average wall shear force (TAWSS), Fractional Flow Reserve (FFR) and the like, wherein the parameters can represent the risk of the blood vessel plaque; for example, low wall shear is associated with plaque growth and high concussion shear index is associated with plaque rupture. Understandably, before the vessel model is predicted through a dynamic parameter prediction algorithm based on machine learning, an initial neural network is constructed based on the current scene, and the vessel model obtained historically is predicted through the neural network to obtain a prediction result; comparing the predicted result with the artificial label and feeding back the result to the neural network so as to update the neural network and enable the neural network to evolve towards the direction of reducing the prediction error; by using a large amount of data (a blood vessel model), the iteration process is repeated thousands of times, and finally the prediction result is close to the artificial standard, so that the dynamic parameter prediction model containing the dynamic parameter prediction algorithm is obtained. Therefore, when the blood vessel model is predicted by the dynamic parameter prediction algorithm based on machine learning, the blood vessel model is input into the dynamic parameter prediction model obtained by training, and the input blood vessel model is predicted by the dynamic parameter prediction algorithm contained in the blood vessel model, so that the hemodynamic parameters such as the wall shear force, the axial plaque stress, the concussion shear index, the time-averaged wall shear force, the blood flow reserve fraction and the like of the blood vessel of the user are obtained. Plaque risk information of the blood vessel of the user is conveniently predicted based on the hemodynamic parameters subsequently, plaque risk processing is conducted on the blood vessel of the user according to the plaque risk information, and the method is beneficial to reducing the fatality rate of cardiovascular and cerebrovascular diseases. It should be noted that, in this embodiment, the dynamical parameter prediction model based on machine learning may be a model obtained by modeling based on a conventional machine learning method, where the conventional machine learning method includes, but is not limited to, a random forest method, a multi-layer perceptron, a bayesian method, a support vector machine, and so on.
Or step D, determining the hemodynamic parameters of the blood vessel of the user according to the blood vessel model and a computational fluid dynamics method.
After a blood vessel model of a blood vessel of a user is generated according to an original medical image, namely a three-dimensional model of the blood vessel of the user is obtained, the blood vessel model can be calculated by a computational fluid dynamics method, so that blood flow dynamics parameters such as wall shear force (WSS), Axial Plaque Stress (APS), concussion shear index (OSI), time average wall shear force (TAWSS), Fractional Flow Reserve (FFR) and the like of the blood vessel of the user are predicted, and the parameters can represent the risk of the blood vessel plaque; for example, low wall shear is associated with plaque growth and high concussion shear index is associated with plaque rupture. Specifically, computational fluid dynamics utilizes a computer to solve fluid mechanics equations, simulate the flow of a simulated fluid, thereby obtaining fluid dynamic parameters such as flow rate, pressure, and the like at various points in a computational domain, and then further obtaining hemodynamic parameters. The steps of the fluid mechanics simulation include: step 1: a mesh corresponding to the vessel model generated by the above process as a 3D model is generated, i.e. the 3D vessel model is generated as a mesh consisting of a plurality of mesh cells. Step 2: obtaining physiological parameters (such as blood pressure, cardiac output, heart rate, ejection fraction, myocardial mass, ventricular volume, coronary volume, etc.) of the user, and calculating parameters (such as coronary inlet flow ═ a × M) of the coronary inlet flow of the user according to the physiological parametersbWhere a and b are given parameters and M is myocardial mass), which is set to a first boundary condition. And 3, step 3: obtaining morphological parameters (such as area, length, volume and the like) of each blood vessel in the blood model, and calculating parameters (such as flow resistance a (current blood vessel area/total blood vessel area)) of flow resistance of each coronary artery outlet according to the morphological parametersbWhere a and b are patient-specific parameters), set it upIs a second boundary condition; and 4, step 4: determining the properties (such as parameters of shear modulus, Young modulus, Poisson ratio and the like) of the fluid of the blood vessel of the user and the material of the vessel wall, and setting the properties as a third boundary condition; and 5, step 5: setting initial conditions of the flow field, wherein the initial conditions can be conventional conditions set in the field; and 6, step 6: other parameters needed to set the fluid simulation solver, such as blood viscosity, density, force between the blood and the vessel wall, etc. It should be noted that the above steps 2 to 6 may be in a random order. And 7, step 7: inputting the parameters (including the first, second and third boundary conditions, initial conditions, other parameters and the like) obtained in the steps into a computer (a personal computer, a cluster computer, a cloud computing platform and a server), and solving the Navier-Stokes equation of the incompressible flow according to the computer and the input parameters to obtain the hemodynamic parameters such as the fluid pressure, the fluid flow speed and the like. And 8, step 8: and performing post-processing on the obtained hemodynamic parameters to obtain final hemodynamic parameters, such as wall shear force, axial plaque stress, concussion shear index, time-averaged wall shear force, fractional flow reserve and the like, and specifically deriving the hemodynamic parameters such as the wall shear force, the axial plaque stress, the concussion shear index, the time-averaged wall shear force, the fractional flow reserve and the like according to the obtained parameters such as flow speed, pressure and the like. For example, the wall shear force may be calculated by calculating a component of the pressure acting on the vessel wall in the tangential direction of the vessel wall; the axial plaque stress can be calculated by calculating the component of the pressure acting on the vessel wall surface in the axial direction of the vessel; the oscillation shear index can be calculated by calculating the distribution of the shear force in a certain period of time; the time-averaged wall shear force can be calculated by calculating the wall shear force acting on the blood vessel within a certain period of time; fractional flow reserve may be calculated by calculating the ratio of pressure to aortic pressure, and so on. Plaque risk information of the blood vessel of the user is conveniently predicted based on the hemodynamic parameters subsequently, plaque risk processing is conducted on the blood vessel of the user according to the plaque risk information, and the method is beneficial to reducing the fatality rate of cardiovascular and cerebrovascular diseases.
Step S30, plaque risk information of the blood vessel of the user is predicted based on the hemodynamic parameters, and the plaque risk information comprises plaque growth risk and plaque rupture risk.
After determining the hemodynamic parameters of the blood vessel of the user according to the blood vessel model, the plaque risk information including the plaque growth risk and the plaque rupture risk of the blood vessel of the user can be predicted directly according to the determined hemodynamic parameters in combination with a preset prediction mode based on a plaque risk calculation formula or a preset prediction mode based on a machine learning plaque risk prediction model. The plaque risk prediction method based on the machine learning can be used for predicting plaque growth risk and plaque rupture risk of the blood vessel of the user by acquiring geometric information of the blood vessel of the user and/or feature information of plaque in the blood vessel of the user based on the original medical image, and then predicting plaque risk information including the plaque growth risk and the plaque rupture risk of the blood vessel of the user according to the geometric information and/or the feature information and the hemodynamic parameters by combining a preset prediction mode based on a plaque risk calculation formula or a preset prediction mode based on a plaque risk prediction model of the machine learning. After the plaque risk information of the blood vessel of the user is predicted, the blood vessel of the user can be monitored according to the plaque risk information, and plaque risk processing is carried out when needed, specifically, the plaque risk processing comprises processing of plaque growth risk and processing of plaque rupture risk, and the method is favorable for reducing the fatality rate of cardiovascular and cerebrovascular diseases.
It can be understood that, after obtaining the plaque risk information of the blood vessel of the user, in order to facilitate medical staff or the user (i.e., a patient) to more intuitively know the risk condition of the blood vessel plaque of the user, the embodiment may further display the plaque risk information in the form of an output quantitative value in the original medical image, so as to provide a visual result for the user, for example, corresponding values are respectively labeled in corresponding regions of the blood vessel in the original image, and the corresponding regions may also be displayed as corresponding colors according to the values, so as to monitor the blood vessel of the user according to the plaque risk information, and perform plaque risk processing when necessary, which is beneficial to reducing the fatality rate of cardiovascular and cerebrovascular diseases. Because past risk assessment can only be carried out by integrating a plurality of factors to judge the grade, a quantized numerical value cannot be obtained, and the method provided by the application can be used for obtaining a quantized index, so that the risk assessment is more detailed.
The embodiment of the application provides a method, a device, equipment and a medium for predicting the risk of blood vessel plaque, which are used for acquiring an original medical image of a blood vessel of a user and generating a blood vessel model of the blood vessel of the user according to the original medical image; determining hemodynamic parameters of the user's blood vessel from the vessel model; predicting plaque risk information for the user's blood vessel based on the hemodynamic parameters, the plaque risk information including a plaque growth risk and a plaque rupture risk. The blood flow dynamics parameters of the blood vessels of the user can be accurately calculated through the blood vessel model generated based on the original medical images of the blood vessels of the user, plaque growth risks and plaque rupture risks of the blood vessels of the user are evaluated based on the blood flow dynamics parameters, plaque risk information of the blood vessels of the user is obtained, and plaques in the blood vessels of the user are effectively monitored according to the plaque growth and rupture conditions in the plaque risk information.
In addition, the present embodiment has the following advantages by executing the vascular plaque risk prediction method of the present application: 1. the method is simple and convenient, and analysis can be performed only by acquiring the coronary image of the patient as an original medical image; and coronary images may be obtained non-invasively, e.g., by CT, MRI, etc.; 2. the risk assessment method can be quantized, only a few factors can be combined to make a grade judgment in the past, and a quantized numerical value cannot be obtained; 3. clinical reference value, the hemodynamic parameters at present, particularly wall shear force, as an index for plaque risk prediction, has been proved by more and more clinical studies and has clinical reference value; 4. full-cycle, the risk of the plaque developing from growth to rupture is predicted.
Further, referring to fig. 3, a second embodiment of the blood vessel plaque risk prediction method of the present application is proposed based on the first embodiment of the blood vessel plaque risk prediction method of the present application, and in the second embodiment, the step of predicting the plaque risk information of the blood vessel of the user based on the hemodynamic parameter includes:
step E, predicting plaque risk information of the blood vessel of the user according to the hemodynamic parameters and a preset prediction mode based on a plaque risk calculation formula;
after a blood vessel model of a blood vessel of a user is generated according to an original medical image and hemodynamic parameters of the blood vessel of the user are further determined according to the blood vessel model, in this embodiment, plaque growth and rupture risks of the blood vessel can be directly predicted through a prediction mode preset based on a plaque risk calculation formula according to the calculated hemodynamic parameters of the blood vessel, so that plaque risk information of the blood vessel of the user is obtained. Understandably, the present application can establish a relationship between hemodynamic parameters and plaque growth, risk of rupture; the relation may be a plaque risk calculation formula, or a plaque risk prediction model obtained through machine learning training. Specifically, each parameter in the hemodynamic parameter may be input into a plaque risk calculation formula, and the plaque risk information of the blood vessel of the user is obtained by calculating the risk of plaque growth and rupture of the blood vessel through the plaque risk calculation formula in combination with the input parameter, where the plaque risk calculation formula is shown as the following formula in this embodiment:
y1＝f1(x1，x2，x3，…，xn)
y2＝f2(x1，x2，x3，…，xn)
where y1 represents the growth risk of plaque and y2 represents the risk of rupture of plaque. Empirical formulas for f1 and f2 for plaque growth and risk of rupture, respectively. x1, x2, x3, …, an denote n parameters, including each of the hemodynamic parameters. For example, x1 represents the value of the wall shear force, x2 represents the value of the oscillating shear index, and so on. More specifically, the plaque risk calculation formula may be of the form:
y1＝a1*x1+a2*x2+a3*x3+…+an*xn
y2＝b1*x1+b2*x2+b3*x3+…+bn*xn
wherein a1, a2, a3, …, an represent the weight values of plaque growth corresponding to n parameters, and b1, b2, b3, …, bn represent the weight values of plaque rupture corresponding to n parameters.
Or step F, predicting the plaque risk information of the blood vessel of the user according to the hemodynamic parameters and a prediction mode of a preset plaque risk prediction model based on machine learning.
The plaque risk prediction method and the device can also predict the hemodynamic parameters through the plaque risk prediction model based on machine learning to obtain the plaque risk information of the blood vessel of the user. Understandably, before the hemodynamic parameters are predicted through a plaque risk prediction model based on machine learning, an initial neural network is built based on a current scene, and the hemodynamic parameters acquired historically are predicted through the neural network to obtain a prediction result; comparing the predicted result with the artificial label and feeding back the result to the neural network so as to update the neural network and enable the neural network to evolve towards the direction of reducing the prediction error; by using a large amount of data (hemodynamic parameters), repeating the above iterative process thousands of times, and finally making the prediction result and the artificial standard close, a plaque risk prediction model containing a plaque risk prediction algorithm is obtained. Therefore, when the hemodynamic parameters are predicted by the plaque risk prediction model based on machine learning, each parameter of the hemodynamic parameters is input into the plaque risk prediction model, and the plaque risk information of the blood vessel of the user is obtained by predicting the plaque growth and rupture risk of the blood vessel by the plaque risk prediction model in combination with the input parameters. It should be noted that the plaque risk prediction model based on machine learning may be based on traditional machine learning methods, including but not limited to random forest method, multi-layer perceptron, bayesian method, support vector machine, etc.
The plaque risk information of the blood vessel of the user can be predicted by combining the hemodynamic parameters with a prediction mode based on a plaque risk calculation formula or a prediction mode based on a plaque risk prediction model of machine learning, so that after the plaque risk information of the blood vessel of the user is predicted, the blood vessel of the user can be monitored according to the plaque risk information, and plaque risk processing is performed when needed, specifically including processing of plaque growth risk and processing of plaque rupture risk, and the reduction of the mortality rate of cardiovascular and cerebrovascular diseases is facilitated.
Further, referring to fig. 4, a third embodiment of the blood vessel plaque risk prediction method of the present application is proposed based on the first embodiment of the blood vessel plaque risk prediction method of the present application, and in the third embodiment, the step of predicting the plaque risk information of the blood vessel of the user based on the hemodynamic parameter further includes:
step G, acquiring geometric information of the blood vessel of the user and/or feature information of plaque in the blood vessel of the user based on the original medical image;
after a blood vessel model of the blood vessel of the user is generated according to the original medical image and the hemodynamic parameter of the blood vessel of the user is further determined according to the blood vessel model, the geometric information of the blood vessel of the user and/or the feature information of the plaque in the blood vessel of the user can be obtained through the original medical image in the embodiment. Specifically, the geometric information of the blood vessel includes information of the diameter, length, cross-sectional area, volume, bifurcation position, bifurcation angle, curvature, and the like of the blood vessel. The geometric information of the blood vessel can be acquired from the original medical image by image processing techniques (such as threshold method, filtering method, machine learning method, etc.). Taking the diameter of the blood vessel as an example, the blood vessel of interest can be extracted from the original medical image by the image processing method (threshold method, filtering method, machine learning method); further, along the center line of the blood vessel, a plane perpendicular to the center line is cut; further obtaining the outline of the blood vessel on the intercepted plane, thereby obtaining the diameter of the blood vessel on the corresponding plane; along the centerline, a series of diameters of the vessel are obtained. According to a series of diameters, the diameters of all the sections of the blood vessel or the average diameter of the blood vessel can be conveniently calculated. Taking the bifurcation angle as an example, after the central lines of two blood vessels are obtained, the spatial relationship between the two central lines can be established, and the included angle formed by the two central lines in the space is the bifurcation angle. It can be understood that after the centerline and the contour of the blood vessel are obtained, the information of the diameter, the length, the cross-sectional area, the volume, the bifurcation position, the bifurcation angle, the curvature, and the like of the blood vessel can be calculated based on a similar method, which is not described in detail herein.
And the characteristic information of the plaque comprises the plaque position, the plaque stenosis degree, the contrast agent concentration corresponding to the plaque, the calcification score, the plaque shape, the plaque size, the plaque type, the reconstruction index, the CT Fat Attenuation Index (FAI), whether to reconstruct positively, whether to napkin the ring sign, whether to calcify punctiform, whether to use low-density plaque and the like. The extraction of feature information of the plaque in this embodiment includes two steps: identification of plaque and calculation of features. Taking the size of the plaque as an example, the plaque can be extracted from the original medical image by the image processing method (threshold method, filtering method, machine learning method) and the size of the plaque can be calculated according to the pixel points occupied by the extracted plaque. Taking the calcification score as an example, after the pixel point corresponding to the plaque is obtained, the calcification part of the blood vessel can be found according to the gray value (HU value) of the pixel point, and the calcification score value corresponding to the blood vessel is calculated according to the calcification score formula. Taking whether the napkin ring feature exists or not as an example, an image part which meets the napkin ring feature can be extracted from the original medical image by the image processing method (threshold method, filtering method and machine learning method), and a segmentation score is given, and if the score is greater than a given threshold value, the napkin ring feature exists in the image. It can be understood that feature information such as a plaque stenosis degree, a contrast agent concentration corresponding to the plaque, a calcification score, a plaque form, a plaque size, a plaque type, a reconstruction index, a CT Fat Attenuation Index (FAI), whether to reconstruct positively, whether to have a napkin ring feature, whether to have punctate calcification, whether to have a low-density plaque, and the like can be obtained based on the image processing method, which is not described in detail herein.
And H, predicting plaque risk information of the blood vessel of the user according to the geometric information and/or the characteristic information and the hemodynamic parameters.
After the hemodynamic parameters of the blood vessel of the user are determined according to the blood vessel model and the geometric information of the blood vessel of the user and/or the feature information of the plaque in the blood vessel of the user are obtained based on the original medical image, the plaque risk information of the blood vessel of the user can be predicted according to the geometric information and/or the feature information and the hemodynamic parameters by combining a preset prediction mode based on a plaque risk calculation formula or a preset prediction mode based on a plaque risk prediction model learned by a machine. For example, the plaque risk information of the blood vessel of the user can be obtained by predicting the plaque growth and rupture risk of the blood vessel in a preset prediction mode based on a plaque risk calculation formula according to the calculated hemodynamic parameters of the blood vessel, the acquired geometric information of the blood vessel of the user and the acquired feature information of the plaque in the blood vessel of the user. The plaque growth and rupture risks of the blood vessels can be predicted in a preset prediction mode based on a plaque risk calculation formula according to the calculated blood vessel hemodynamic parameters and the acquired geometric information of the blood vessels of the user, and plaque risk information of the blood vessels of the user is obtained; the plaque growth and rupture risks of the blood vessels can be predicted in a preset prediction mode of a plaque risk prediction model based on machine learning according to the calculated blood vessel hemodynamic parameters and the acquired feature information of the plaque in the blood vessels of the user, and plaque risk information of the blood vessels of the user and the like are obtained. The plaque risk monitoring system is convenient to monitor blood vessels of a user according to plaque risk information, carries out plaque risk treatment when needed, specifically comprises treatment on plaque growth risks and treatment on plaque rupture risks, and is favorable for reducing the fatality rate of cardiovascular and cerebrovascular diseases.
Further, the step of predicting plaque risk information of the blood vessel of the user according to the geometric information and/or the characteristic information and the hemodynamic parameter comprises:
step I, predicting plaque risk information of the blood vessel of the user according to the geometric information and/or the characteristic information and the hemodynamic parameters in combination with a preset prediction mode based on a plaque risk calculation formula;
after a blood vessel model of a blood vessel of a user is generated according to an original medical image and hemodynamic parameters of the blood vessel of the user are further determined according to the blood vessel model, in this embodiment, a risk of plaque growth and rupture of the blood vessel can be predicted through a preset prediction mode based on a plaque risk calculation formula according to the hemodynamic parameters of the blood vessel obtained through calculation, and the obtained geometric information of the blood vessel of the user and/or feature information of plaque in the blood vessel of the user, so that plaque risk information of the blood vessel of the user is obtained. Specifically, the plaque risk information of the blood vessel of the user is obtained by predicting the plaque growth and rupture risk of the blood vessel in a preset prediction mode based on a plaque risk calculation formula according to the calculated hemodynamic parameters of the blood vessel of the user, the obtained geometric information of the blood vessel of the user and the obtained feature information of the plaque in the blood vessel of the user; or predicting the plaque growth and rupture risk of the blood vessel in a preset prediction mode based on a plaque risk calculation formula according to the calculated blood vessel hemodynamic parameters and the acquired geometric information of the blood vessel of the user to obtain the plaque risk information of the blood vessel of the user; or predicting the plaque growth and rupture risk of the blood vessel in a preset prediction mode based on a plaque risk calculation formula according to the calculated blood vessel hemodynamic parameters and the acquired feature information of the plaque in the blood vessel of the user to obtain the plaque risk information of the blood vessel of the user. As can be appreciated, the present application may establish a relationship between parameters such as hemodynamic parameters, geometric information of a blood vessel of a user, and/or feature information of plaque in a blood vessel of a user, and plaque growth and rupture risk; the relation may be a plaque risk calculation formula, or a plaque risk prediction model obtained through machine learning training. Specifically, each parameter, geometric information and/or feature information in the hemodynamic parameter may be input into a plaque risk calculation formula, and the plaque risk calculation formula may calculate the risk of plaque growth and rupture of the blood vessel by combining the input parameter, so as to obtain plaque risk information of the blood vessel of the user, where the plaque risk calculation formula is shown in the following formula in this embodiment:
y1＝f1(x1，x2，x3，…，xn)
y2＝f2(x1，x2，x3，…，xn)
where y1 represents the growth risk of plaque and y2 represents the risk of rupture of plaque. Empirical formulas for f1 and f2 for plaque growth and risk of rupture, respectively. x1, x2, x3, …, an represent n parameters including hemodynamic parameters, and geometric information of the user's blood vessels and feature information of plaque. For example, x1 represents the value of the wall shear force, x10 represents whether there is a positive reconstruction, is 1, is 0, etc. More specifically, the plaque risk calculation formula may be of the form:
y1＝a1*x1+a2*x2+a3*x3+…+an*xn
y2＝b1*x1+b2*x2+b3*x3+…+bn*xn
wherein a1, a2, a3, …, an represent the weight values of plaque growth corresponding to n parameters, and b1, b2, b3, …, bn represent the weight values of plaque rupture corresponding to n parameters.
Or step J, predicting the plaque risk information of the blood vessel of the user according to the geometric information and/or the characteristic information and the hemodynamic parameters in combination with a preset prediction mode of a plaque risk prediction model based on machine learning.
The plaque risk prediction method and the device can also predict the hemodynamic parameters, the geometric information and/or the characteristic information through the plaque risk prediction model to obtain the plaque risk information of the blood vessel of the user. The plaque risk information of the blood vessel of the user can be predicted according to geometric information, characteristic information and hemodynamic parameters in combination with a preset prediction mode of a plaque risk prediction model based on machine learning; the plaque risk information of the blood vessel of the user can be predicted according to the geometric information and the hemodynamic parameters in combination with a prediction mode of a preset plaque risk prediction model based on machine learning; the plaque risk information of the blood vessel of the user can be predicted according to the feature information and the hemodynamic parameters in combination with a preset prediction mode of a plaque risk prediction model based on machine learning. The method includes the steps that before a plaque risk prediction model based on machine learning is used for predicting hemodynamic parameters, geometric information and/or characteristic information, an initial neural network is built based on a current scene, and the hemodynamic parameters, the geometric information and/or the characteristic information acquired historically are predicted through the neural network to obtain a prediction result; comparing the predicted result with the artificial label and feeding back the result to the neural network so as to update the neural network and enable the neural network to evolve towards the direction of reducing the prediction error; by using a large amount of data (hemodynamic parameters and geometric information and/or characteristic information), the iterative process is repeated thousands of times, and finally the prediction result is close to the artificial standard, so that a plaque risk prediction model containing a plaque risk prediction algorithm is obtained. Therefore, when the hemodynamic parameters and the geometric information and/or the characteristic information are predicted by the plaque risk prediction model based on machine learning, each parameter of the hemodynamic parameters and the geometric information and/or the characteristic information are input into the plaque risk prediction model, and the plaque risk information of the blood vessel of the user is obtained by predicting the growth and rupture risk of the blood vessel plaque through the plaque risk prediction model by combining the input parameters. It should be noted that, in the present embodiment, the plaque risk prediction model based on machine learning may be based on a traditional machine learning method, where the traditional machine learning method includes, but is not limited to, a random forest method, a multi-layer perceptron, a bayesian method, a support vector machine, and so on.
According to the embodiment, the plaque risk information of the blood vessel of the user can be predicted through the hemodynamic parameters, the geometric information and/or the characteristic information, and by combining the prediction mode based on the plaque risk calculation formula or the prediction mode based on the plaque risk prediction model learned by a machine, after the plaque risk information of the blood vessel of the user is predicted, the blood vessel of the user can be monitored according to the plaque risk information, and the plaque risk processing is performed when needed, specifically including the processing of the plaque growth risk and the processing of the plaque rupture risk, so that the accuracy of a prediction result is higher, and the reduction of the mortality of cardiovascular and cerebrovascular diseases is more facilitated.
Further, the application also provides a blood vessel plaque risk prediction device.
Referring to fig. 5, fig. 5 is a functional module schematic diagram of a blood vessel plaque risk prediction device according to a first embodiment of the present application.
The vascular plaque risk prediction device includes:
an obtaining module 10, configured to obtain an original medical image of a blood vessel of a user, and generate a blood vessel model of the blood vessel of the user according to the original medical image;
a determining module 20 for determining hemodynamic parameters of the user's blood vessel from the blood vessel model;
a prediction module 30 configured to predict plaque risk information of the blood vessel of the user based on the hemodynamic parameter, where the plaque risk information includes a plaque growth risk and a plaque rupture risk.
Furthermore, the present application also provides a medium, preferably a computer readable storage medium, on which a vascular plaque risk prediction program is stored, which when executed by a processor, implements the steps of the embodiments of the vascular plaque risk prediction method described above.
Furthermore, the present application also provides a computer program product comprising a computer program, which when executed by a processor, implements the steps of the embodiments of the vascular plaque risk prediction method described above.
In the embodiments of the blood vessel plaque risk prediction device, the computer-readable storage medium, and the computer program product of the present application, all technical features of the embodiments of the blood vessel plaque risk prediction method are included, and the description and explanation contents are basically the same as those of the embodiments of the blood vessel plaque risk prediction method, and are not repeated herein.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present application or a part contributing to the prior art may be embodied in the form of a software product, where the computer software product is stored in a storage medium (e.g., a ROM/RAM, a magnetic disk, and an optical disk), and includes a plurality of instructions for enabling a terminal device (which may be a fixed terminal, such as an internet of things smart device including smart homes, such as a smart air conditioner, a smart lamp, a smart power supply, and a smart router, or a mobile terminal, including a smart phone, a wearable networked AR/VR device, a smart sound box, and a network device such as an auto-driven automobile) to execute the method according to the embodiments of the present application.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application, or which are directly or indirectly applied to other related technical fields, are included in the scope of the present application.
Claims (10)
1. A vascular plaque risk prediction method is characterized by comprising the following steps:
acquiring an original medical image of a user blood vessel, and generating a blood vessel model of the user blood vessel according to the original medical image;
determining hemodynamic parameters of the user's blood vessel from the vessel model;
predicting plaque risk information for the user's blood vessel based on the hemodynamic parameters, the plaque risk information including a plaque growth risk and a plaque rupture risk.
2. The method of predicting plaque risk in blood vessels of claim 1 wherein said step of predicting plaque risk information for said user's blood vessels based on said hemodynamic parameters comprises:
predicting plaque risk information of the blood vessel of the user according to the hemodynamic parameters and a preset prediction mode based on a plaque risk calculation formula; or
And predicting plaque risk information of the blood vessel of the user according to the hemodynamic parameters and a prediction mode of a preset plaque risk prediction model based on machine learning.
3. The method of predicting plaque risk in blood vessels of claim 2 wherein said step of predicting plaque risk information for said user's blood vessels based on said hemodynamic parameters further comprises:
acquiring geometric information of the blood vessel of the user and/or characteristic information of plaque in the blood vessel of the user based on the original medical image;
predicting plaque risk information of the blood vessel of the user according to the geometric information and/or the characteristic information and the hemodynamic parameter.
4. The method for predicting plaque risk in blood vessels according to claim 3, wherein said step of predicting plaque risk information of said user's blood vessels based on said geometric information and/or said feature information and said hemodynamic parameters comprises:
predicting plaque risk information of the blood vessel of the user according to the geometric information and/or the characteristic information and the hemodynamic parameters in combination with a preset prediction mode based on a plaque risk calculation formula; or
And predicting the plaque risk information of the blood vessel of the user according to the geometric information and/or the characteristic information and the hemodynamic parameters in combination with a prediction mode of a preset plaque risk prediction model based on machine learning.
5. The method of predicting vascular plaque risk of claim 1 wherein the step of generating a vessel model of the user's vessel from the raw medical image comprises:
generating a blood vessel model of the blood vessel of the user according to a preset image processing method and the original medical image, wherein the preset image processing method comprises a threshold method and a filtering method; or
And generating a blood vessel model of the blood vessel of the user according to a blood vessel prediction algorithm based on machine learning and the original medical image.
6. The method of predicting vascular plaque risk of claim 1 wherein the step of determining hemodynamic parameters of the user's blood vessel based on the vessel model comprises:
determining hemodynamic parameters of the blood vessel of the user according to the blood vessel model and a dynamic parameter prediction algorithm based on machine learning; or
And determining the hemodynamic parameters of the blood vessel of the user according to the blood vessel model and the computational fluid dynamics method.
7. The method according to claim 1, wherein the hemodynamic parameter comprises one or more of wall shear, axial plaque stress, concussion shear index, time-averaged wall shear, fractional flow reserve.
8. A vascular plaque risk prediction device, comprising:
the acquisition module is used for acquiring an original medical image of a blood vessel of a user and generating a blood vessel model of the blood vessel of the user according to the original medical image;
a determining module for determining hemodynamic parameters of the user's blood vessel from the blood vessel model;
a prediction module for predicting plaque risk information of the user's blood vessel based on the hemodynamic parameter, the plaque risk information including a plaque growth risk and a plaque rupture risk.
9. A vascular plaque risk prediction device comprising a memory, a processor, and a vascular plaque risk prediction program stored on the memory and executable on the processor, the vascular plaque risk prediction program when executed by the processor implementing the steps of the vascular plaque risk prediction method of any one of claims 1-7.
10. A medium which is a computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a blood vessel plaque risk prediction program which, when executed by a processor, implements the steps of the blood vessel plaque risk prediction method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111296678.5A CN114010157A (en) | 2021-11-03 | 2021-11-03 | Blood vessel plaque risk prediction method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111296678.5A CN114010157A (en) | 2021-11-03 | 2021-11-03 | Blood vessel plaque risk prediction method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114010157A true CN114010157A (en) | 2022-02-08 |
Family
ID=80060387
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111296678.5A Pending CN114010157A (en) | 2021-11-03 | 2021-11-03 | Blood vessel plaque risk prediction method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114010157A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114693622A (en) * | 2022-03-22 | 2022-07-01 | 电子科技大学 | Plaque erosion automatic detection system based on artificial intelligence |
| CN114972165A (en) * | 2022-03-24 | 2022-08-30 | 中山大学孙逸仙纪念医院 | Method and device for measuring time-average shearing force |
| CN117524487A (en) * | 2024-01-04 | 2024-02-06 | 首都医科大学附属北京天坛医院 | Artificial intelligence-based method and system for evaluating risk of arteriosclerotic plaque |
-
2021
- 2021-11-03 CN CN202111296678.5A patent/CN114010157A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114693622A (en) * | 2022-03-22 | 2022-07-01 | 电子科技大学 | Plaque erosion automatic detection system based on artificial intelligence |
| CN114693622B (en) * | 2022-03-22 | 2023-04-07 | 电子科技大学 | Plaque erosion automatic detection system based on artificial intelligence |
| CN114972165A (en) * | 2022-03-24 | 2022-08-30 | 中山大学孙逸仙纪念医院 | Method and device for measuring time-average shearing force |
| CN114972165B (en) * | 2022-03-24 | 2024-03-15 | 中山大学孙逸仙纪念医院 | Method and device for measuring time average shearing force |
| CN117524487A (en) * | 2024-01-04 | 2024-02-06 | 首都医科大学附属北京天坛医院 | Artificial intelligence-based method and system for evaluating risk of arteriosclerotic plaque |
| CN117524487B (en) * | 2024-01-04 | 2024-03-29 | 首都医科大学附属北京天坛医院 | Artificial intelligence-based method and system for evaluating risk of arteriosclerotic plaque |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6522175B2 (en) | System and method for estimating blood flow characteristics from vessel shape and physiology | |
| EP3723038B1 (en) | Fast calculation method and system employing plaque stability index of medical image sequence | |
| CN108511075B (en) | Method and system for non-invasively acquiring fractional flow reserve | |
| CN114010157A (en) | Blood vessel plaque risk prediction method, device, equipment and medium | |
| JP6667999B2 (en) | Image processing apparatus, image processing method, and program | |
| US20210210209A1 (en) | Systems and methods for identifying and modeling unresolved vessels in imagebased patient-specific hemodynamic models | |
| EP3277169B1 (en) | Systems and methods for estimating virtual perfusion images | |
| JP2020503095A (en) | Machine learning of anatomical model parameters | |
| JP6484760B2 (en) | Modeling collateral blood flow for non-invasive blood flow reserve ratio (FFR) | |
| JP2016533815A (en) | System and method for identifying personalized vascular grafts from patient-specific anatomical data | |
| JP2011500187A5 (en) | ||
| US11468570B2 (en) | Method and system for acquiring status of strain and stress of a vessel wall | |
| Glaßer et al. | Combined visualization of wall thickness and wall shear stress for the evaluation of aneurysms | |
| CN107665737A (en) | Vascular wall stress-strain state acquisition methods, computer-readable medium and system | |
| Löhner et al. | Applications of patient‐specific CFD in medicine and life sciences | |
| Iqbal et al. | Texture analysis of ultrasound images of chronic kidney disease | |
| US11727570B2 (en) | Methods and systems for determining coronary hemodynamic characteristic(s) that is predictive of myocardial infarction | |
| Prakash et al. | Binary photoacoustic tomography for improved vasculature imaging | |
| Auricchio et al. | A clinically applicable stochastic approach for noninvasive estimation of aortic stiffness using computed tomography data | |
| Gharaibeh et al. | Deep learning segmentation of coronary calcified plaque from intravascular optical coherence tomography (IVOCT) images with application to finite element modeling of stent deployment | |
| KR101530352B1 (en) | Cfd modeling and analysis method based on material properties | |
| Sen et al. | A comparison of medical image segmentation methods for cerebral aneurysm computational hemodynamics | |
| CN111755104B (en) | Heart state monitoring method and system, electronic equipment and storage medium | |
| Shalev et al. | Intravascular optical coherence tomography image analysis method | |
| Cerrolaza et al. | Modeling human tissues: an efficient integrated methodology |
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 |