CN111755104B - Heart state monitoring method and system, electronic equipment and storage medium - Google Patents
Heart state monitoring method and system, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111755104B CN111755104B CN202010421667.4A CN202010421667A CN111755104B CN 111755104 B CN111755104 B CN 111755104B CN 202010421667 A CN202010421667 A CN 202010421667A CN 111755104 B CN111755104 B CN 111755104B
- Authority
- CN
- China
- Prior art keywords
- data
- heart
- coronary
- patient
- dimensional model
- 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.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 85
- 238000000034 method Methods 0.000 title claims abstract description 54
- 230000000747 cardiac effect Effects 0.000 claims abstract description 78
- 210000004351 coronary vessel Anatomy 0.000 claims abstract description 77
- 238000002586 coronary angiography Methods 0.000 claims abstract description 53
- 230000033001 locomotion Effects 0.000 claims abstract description 37
- 210000000038 chest Anatomy 0.000 claims description 36
- 230000036541 health Effects 0.000 claims description 25
- 238000007781 pre-processing Methods 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 12
- 238000010276 construction Methods 0.000 claims description 7
- 238000013185 thoracic computed tomography Methods 0.000 claims description 7
- 238000002583 angiography Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 238000004088 simulation Methods 0.000 abstract description 12
- 238000012800 visualization Methods 0.000 abstract description 8
- 230000000007 visual effect Effects 0.000 abstract 1
- 238000002591 computed tomography Methods 0.000 description 34
- 239000000243 solution Substances 0.000 description 9
- 210000004204 blood vessel Anatomy 0.000 description 8
- 230000008569 process Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 208000019622 heart disease Diseases 0.000 description 4
- 230000000737 periodic effect Effects 0.000 description 4
- 238000010009 beating Methods 0.000 description 3
- 230000017531 blood circulation Effects 0.000 description 3
- 230000008602 contraction Effects 0.000 description 3
- 208000029078 coronary artery disease Diseases 0.000 description 3
- 238000003709 image segmentation Methods 0.000 description 3
- 201000000057 Coronary Stenosis Diseases 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 230000010247 heart contraction Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 210000004165 myocardium Anatomy 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 210000001367 artery Anatomy 0.000 description 1
- 230000036772 blood pressure Effects 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 239000002872 contrast media Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000010419 fine particle Substances 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000036285 pathological change Effects 0.000 description 1
- 231100000915 pathological change Toxicity 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000002601 radiography Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000023718 relaxation of cardiac muscle Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000001020 rhythmical effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- 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
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
- G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30048—Heart; Cardiac
Abstract
The embodiment of the invention provides a heart state monitoring method, a heart state monitoring system, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring real-time cardiac data of a patient; synchronizing a pre-constructed motion state of the digital heart of the patient based on the real-time cardiac data; the digital heart comprises a basic heart three-dimensional model and a coronary artery three-dimensional model, wherein the basic heart three-dimensional model is constructed on the basis of chest CT data of a patient, and the coronary artery three-dimensional model is constructed on the basis of coronary angiography data of the patient. The heart state monitoring method, the heart state monitoring system, the electronic equipment and the storage medium provided by the embodiment of the invention establish a digital twin system between the human heart and the simulation model, realize dynamic visualization of the human heart, facilitate clear and visual understanding of the heart state of a patient, synchronously update the motion state of the digital heart based on real-time heart data, and realize real-time monitoring of the heart state.
Description
Technical Field
The invention relates to the technical field of digital simulation, in particular to a heart state monitoring method, a heart state monitoring system, electronic equipment and a storage medium.
Background
With the application and development of internet technology in the medical industry, intelligent medical care is receiving more and more attention. Wisdom medical treatment utilizes the most advanced internet of things through making the regional medical information platform of health archives, realizes the interdynamic between patient and medical staff, medical institution, the medical equipment, reaches informationization gradually.
Heart disease, especially coronary heart disease, is a disease that seriously threatens human health, and has the characteristics of high morbidity, high disability rate and high mortality. The heart condition monitoring system can be used for monitoring the heart condition of a patient with the heart disease, can assist doctors in tracking the disease condition and providing rehabilitation advice, and is beneficial to the recovery of the health of the patient with the heart disease.
At present, a health monitoring platform based on intelligent medical treatment is only limited to human body data analysis, and the heart state cannot be dynamically monitored in real time.
Disclosure of Invention
The embodiment of the invention provides a heart state monitoring method, a heart state monitoring system, electronic equipment and a storage medium, which are used for solving the technical problem that the existing health monitoring platform cannot dynamically monitor the heart state in real time.
In a first aspect, an embodiment of the present invention provides a cardiac state monitoring method, including:
acquiring real-time cardiac data of a patient;
synchronizing a pre-constructed motion state of the patient's digital heart based on the real-time cardiac data;
wherein the digital heart comprises a base three-dimensional model of the heart constructed based on thoracic CT data of the patient and a three-dimensional model of the coronary artery constructed based on coronary angiography data of the patient.
Optionally, the method for constructing a digital heart specifically includes:
inputting the chest CT data into a basic heart three-dimensional reconstruction network to obtain a basic heart three-dimensional model output by the basic heart three-dimensional reconstruction network;
inputting the coronary angiography data into a coronary three-dimensional reconstruction network to obtain the coronary three-dimensional model output by the coronary three-dimensional reconstruction network;
wherein the basic heart three-dimensional reconstruction network is trained based on sample chest CT data and a sample basic heart three-dimensional model, the coronary three-dimensional reconstruction network is trained based on sample coronary angiography data and a sample coronary three-dimensional model, and the sample coronary three-dimensional model is determined based on sample coronary CTA data.
Optionally, the synchronizing the pre-constructed motion state of the digital heart of the patient based on the real-time cardiac data further comprises:
initializing a heart beat of the basic heart three-dimensional model based on a basic electrocardiogram of the patient;
initializing coronary vessel motion of the coronary three-dimensional model based on the patient's coronary angiography video.
Optionally, the acquiring real-time cardiac data of the patient further comprises:
preprocessing the thoracic CT data and the coronary angiography data;
wherein the pre-processing comprises image de-noising and/or image enhancement.
Optionally, obtaining basic health data of the patient;
updating the patient's cardiac state monitoring data based on the patient's basic health data and the patient's motion state of the digital heart.
Optionally, if a cardiac state monitoring data query request sent by the client is received, the cardiac state monitoring data corresponding to the patient of the cardiac state monitoring data query request is returned.
In a second aspect, embodiments of the present invention provide a cardiac condition monitoring system, including:
the data acquisition module is used for acquiring real-time cardiac data of a patient;
a digital heart update module for synchronizing a pre-constructed motion state of the patient's digital heart based on the real-time cardiac data;
wherein the digital heart comprises a base three-dimensional model of the heart constructed based on the patient's thoracic CT data and a three-dimensional model of the coronary artery constructed based on the patient's coronary angiography data.
In a third aspect, an embodiment of the present invention provides an electronic device, including: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of cardiac condition monitoring as described in the first aspect when executing the program.
In a fourth aspect, embodiments of the invention provide a non-transitory computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the cardiac state monitoring method according to the first aspect.
According to the heart state monitoring method, the heart state monitoring system, the electronic equipment and the storage medium, the basic heart three-dimensional model is constructed based on the chest CT data, the coronary artery three-dimensional model is constructed based on the coronary angiography data, the basic heart three-dimensional model and the coronary artery three-dimensional model are combined to construct the digital heart, the digital twinborn system between the human heart and the simulation model is established, dynamic visualization of the human heart is achieved, the heart state of a patient can be clearly and visually known conveniently, meanwhile, the motion state of the digital heart is synchronously updated based on real-time heart data, and real-time monitoring of the heart state is achieved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a cardiac condition monitoring method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a cardiac condition monitoring system according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
A Digital Twin (Digital Twin) is a simulation process integrating multiple disciplines, multiple physical quantities, multiple scales and multiple probabilities by fully utilizing data such as a physical model, sensor updating and operation history and the like, and mapping is completed in a virtual space, so that the full life cycle process of corresponding entity equipment is reflected. The digital twin can map various attributes of the physical equipment into a virtual space through various digital means such as a design tool, a simulation tool, an internet of things, virtual reality and the like to form a digital mirror image which can be disassembled, copied, transferable, modifiable, deleteable and repeatedly operated. The digital twin can also deduce some indexes which cannot be directly measured originally by machine learning by collecting direct data of limited physical sensor indexes and by means of a large sample library. Therefore, the evaluation of the current state, the diagnosis of problems occurring in the past and the prediction of future trends are realized, the analysis result is given, various possibilities are simulated, and more comprehensive decision support is provided. At present, digital twins are mainly applied to industrial-grade mathematical and physical models, and the cardiac state monitoring method provided by the embodiment of the invention applies a digital twins technology to the generation of a cardiac model.
Fig. 1 is a schematic flow chart of a cardiac state monitoring method according to an embodiment of the present invention, and as shown in fig. 1, the cardiac state monitoring method according to the embodiment of the present invention includes:
the digital heart comprises a basic heart three-dimensional model and a coronary artery three-dimensional model, wherein the basic heart three-dimensional model is constructed on the basis of chest CT data of a patient, and the coronary artery three-dimensional model is constructed on the basis of coronary angiography data of the patient.
Specifically, based on the patient's periodic physical examination data, chest CT data and coronary data may be acquired for the patient. Among them, chest CT (computed Tomography) data is an image of a heart structure of a human body acquired by X-ray computed Tomography, coronary angiography data is an image sequence of a coronary angiography video, a catheter is inserted into a coronary artery selectively to the left and right after puncturing the artery percutaneously and a contrast agent is injected, and a dynamic image of a developing process is recorded. The coronary angiography data can observe the coronary stenosis part and the pathological change degree of the patient, and can also monitor the influence of the coronary stenosis on the blood flow. Based on the chest CT data of the patient, a basic heart three-dimensional model can be constructed, so that the heart of the patient is simulated; based on the coronary angiography data of the patient, a three-dimensional model of the coronary artery can be constructed, so that the coronary artery blood vessel of the patient can be simulated. The digital heart of the patient can be constructed by combining the basic heart three-dimensional model and the coronary artery three-dimensional model. The digital heart can not only represent the basic structure of the heart, but also represent the structure of coronary vessels, thereby realizing the visualization of the heart of a patient.
After the digital heart of the patient is constructed, the real-time heart data of the patient can be acquired through the intelligent wearable device, the intelligent wearable device can be an intelligent bracelet, an intelligent watch and the like, and the real-time heart data of the patient can be a real-time electrocardiogram. The electrocardiogram is used for reflecting the electrical activity change rule of each cardiac cycle of the heart, the electrical activity change rule of each cardiac cycle of the heart can be obtained based on the real-time electrocardiogram, and the digital heart is driven to beat based on the electrical activity change rule, so that the real-time synchronous beating of the human heart and the digital heart is realized. The rhythmic beating of the heart depends on the periodic contraction and relaxation of cardiac muscle, coronary vessels are attached to the surface of the heart, the contraction and relaxation of the cardiac muscle can cause the deformation of the coronary vessels, and the contraction and relaxation of the cardiac muscle can influence the blood flow in the coronary vessels, so that the beating of the heart is updated to update the motion of the coronary vessels of the heart.
It should be noted that the cardiac condition monitoring method provided by the embodiment of the present invention can be used for dynamic visualization of the heart of a patient with coronary heart disease, but is not used for diagnosis activities of coronary heart disease and other cardiac diseases.
According to the heart state monitoring method provided by the embodiment of the invention, the basic heart three-dimensional model is constructed based on the chest CT data, the coronary artery three-dimensional model is constructed based on the coronary angiography data, the basic heart three-dimensional model and the coronary artery three-dimensional model are combined to construct the digital heart, the digital twinning system between the human heart and the simulation model is established, the dynamic visualization of the human heart is realized, the heart state of a patient can be clearly and intuitively known conveniently, meanwhile, the motion state of the digital heart is synchronously updated based on the real-time heart data, and the real-time monitoring of the heart state is realized.
Based on the above embodiment, in the cardiac state monitoring method, the construction method of the digital heart specifically includes:
inputting chest CT data into a basic heart three-dimensional reconstruction network to obtain a basic heart three-dimensional model;
inputting coronary angiography data into a coronary three-dimensional reconstruction network to obtain a coronary three-dimensional model;
the basic heart three-dimensional reconstruction network is obtained based on sample chest CT data and sample basic heart three-dimensional model training, the coronary artery three-dimensional reconstruction network is obtained based on sample coronary angiography data and sample coronary artery three-dimensional model training, and the sample coronary artery three-dimensional model is determined based on sample coronary artery CTA data.
Specifically, after chest CT data and coronary angiography data of a patient are obtained, the chest CT data and the coronary angiography data are respectively input into a basic heart three-dimensional reconstruction network and a coronary three-dimensional reconstruction network, a basic heart three-dimensional model and a coronary three-dimensional model output by the basic heart three-dimensional reconstruction network and the coronary three-dimensional reconstruction network are respectively obtained, and the basic heart three-dimensional model and the coronary three-dimensional model are combined to construct the digital heart. The basic heart three-dimensional reconstruction network is used for three-dimensional reconstruction of the heart based on chest CT data and an artificial intelligence segmentation technology, and the coronary artery three-dimensional reconstruction network is used for three-dimensional reconstruction of the coronary artery based on coronary angiography data and the artificial intelligence segmentation technology.
Before the digital heart is constructed, a basic heart three-dimensional reconstruction network and a coronary three-dimensional reconstruction network can be obtained through pre-training, and the specific training mode of the basic heart three-dimensional reconstruction network is as follows: firstly, a large amount of sample chest CT data are collected, the sample chest CT data are input into medical three-dimensional software, a heart three-dimensional model output by the medical three-dimensional software is obtained, and the heart three-dimensional model output by the medical three-dimensional software is manually corrected to be used as a sample basic heart three-dimensional model. And then, inputting the sample chest CT data and the sample basic heart three-dimensional model into the initial network for training, thereby obtaining a basic heart three-dimensional reconstruction network.
The specific training mode of the coronary artery three-dimensional reconstruction network is as follows: first, a large number of sample coronary CTA data and sample coronary angiography data are collected. The coronary blood vessel is divided into two branches, one branch is composed of a main blood vessel and a plurality of tiny blood vessels. The sample coronary CTA data is used for characterizing the main coronary vessels, and the sample coronary angiography data is used for characterizing the coronary vessels and the trend and the shape of the vessels. Inputting the sample coronary artery CTA data into medical three-dimensional software to obtain a coronary artery three-dimensional model output by the medical three-dimensional software, and manually correcting the coronary artery three-dimensional model output by the medical three-dimensional software to obtain a sample coronary artery three-dimensional model. And then inputting the sample coronary angiography data and the sample coronary three-dimensional model into the initial network for training, thereby obtaining the coronary three-dimensional reconstruction network.
It should be noted that, a weak supervised learning method is adopted for training of the coronary artery three-dimensional reconstruction network, that is, the sample coronary artery CTA data and the sample coronary artery angiography data may not belong to the same patient, and the sample coronary artery three-dimensional model determined based on the sample coronary artery CTA data may not be an accurate mark of the coronary artery three-dimensional model corresponding to the sample coronary artery angiography data. By continuously adjusting the parameters of the initial network, the errors between the coronary artery three-dimensional model output by the initial network and the sample coronary artery three-dimensional model and between the coronary artery angiography data obtained by projecting the coronary artery three-dimensional model output by the initial network and the sample coronary artery angiography data are minimized. The coronary three-dimensional reconstruction network is trained through a weak supervised learning method, so that the construction of the coronary three-dimensional reconstruction network can be realized under the condition that a large amount of coronary CTA data and coronary angiography data of a sample of the same patient cannot be obtained, and the precision of the coronary three-dimensional reconstruction network is ensured.
According to the heart state monitoring method provided by the embodiment of the invention, the digital heart is constructed through the basic heart three-dimensional reconstruction network and the coronary three-dimensional reconstruction network, the coronary three-dimensional reconstruction network is trained by using a weak supervision learning method, the construction of the coronary three-dimensional reconstruction network can be realized when a large number of training sets cannot be obtained, and meanwhile, the precision of the coronary three-dimensional reconstruction network is ensured.
In any of the above embodiments, the method for monitoring cardiac status further includes, before step 120:
initializing the heart beat of a basic heart three-dimensional model based on a basic electrocardiogram of a patient;
coronary vessel motion of a three-dimensional model of the coronary is initialized based on the patient's coronary angiography video.
Specifically, the digital heart constructed based on the chest CT data and the coronary angiography data is a static model, and in order to realize the simulated motion of the digital heart, the heart beat of the basic heart three-dimensional model can be initialized based on the basic electrocardiogram of the patient, and the coronary vessel motion of the coronary three-dimensional model can be initialized based on the coronary angiography video of the patient. The basic electrocardiogram is historical detection data of the patient, the basic electrocardiogram can be from periodic physical examination data of the patient and can also be acquired through intelligent wearable equipment of the patient, and the embodiment of the invention is not particularly limited. Coronary vessel motion includes changes in the shape of coronary vessels and blood flow in coronary vessels. The specific process of motion simulation of the digital heart may be: based on the electrocardio frequency obtained by the basic electrocardiogram, three-dimensional software of animation is used for adding heartbeat animation simulation to the digital heart, the simulation result is compared with the result of coronary artery in the coronary angiography video, and when the coronary artery blood vessel in the animation simulation is projected to a two-dimensional plane and is consistent with the blood vessel motion in the coronary angiography video, the motion frequency of the motion simulation can be determined.
According to the heart state monitoring method provided by the embodiment of the invention, the heart beating of the basic heart three-dimensional model is initialized based on the basic electrocardiogram of the patient, and the coronary vessel movement of the coronary three-dimensional model is initialized based on the coronary angiography video of the patient, so that the dynamic visualization of the human heart is realized, and the heart state of the patient can be conveniently and clearly understood.
In any of the above embodiments, the method for monitoring cardiac status further includes, before step 110:
preprocessing the chest CT data and the coronary angiography data;
wherein the preprocessing comprises image denoising and/or image enhancement.
Specifically, image data obtained by a medical imaging device is affected by noise, organ movement, improper injection rate and dosage selection during radiography, inaccurate scanning time holding time and other factors during imaging, and has certain defects in the aspects of contrast, brightness and the like. The image denoising is to eliminate noise information in the image data, for example, the chest CT data may be processed by using median filtering or gaussian smoothing, so as to eliminate noise information such as snow points and fine particles in the chest CT data, and meanwhile, the heart edge features are retained, which is beneficial to subsequently performing image segmentation on the chest CT data. The image enhancement is to highlight the interesting features in the image, suppress the uninteresting features and enlarge the difference between different features in the image, for example, the coronary angiography data can be processed by using a head cap method or wavelet transformation, and the contrast between the coronary blood vessels and the background can be enhanced, so that the texture of the coronary blood vessels, especially the fine blood vessels, is clearer.
In the embodiment of the present invention, the process of preprocessing the chest CT data and the coronary angiography data may adopt one of the above methods, or may adopt a plurality of the above methods, and the selection of the preprocessing method and the specific algorithm of each preprocessing method are not specifically limited in the embodiment of the present invention.
According to the heart state monitoring method provided by the embodiment of the invention, the chest CT data and the coronary angiography data are preprocessed, so that noise information is eliminated, image characteristics of the heart and coronary blood vessels are reserved and highlighted, and the method is favorable for constructing a basic heart three-dimensional model and a coronary three-dimensional model by carrying out image segmentation based on the chest CT data and the coronary angiography data.
In accordance with any of the above embodiments, the cardiac state monitoring method further comprises:
acquiring basic health data of a patient;
updating the cardiac state monitoring data of the patient based on the basic health data of the patient and the motion state of the digital heart of the patient.
Specifically, the basic health data of the patient may include body temperature, blood pressure, heart rate, and the like, and the basic health data may be acquired through the intelligent wearable device, or the basic health data may be initialized by using the periodic physical examination data, and updated through the real-time data acquired by the intelligent wearable device. Because the data collected by the medical equipment in the physical examination contains a large amount of redundant information and noise data, the original physical examination data can be cleaned and subjected to redundancy removal before the basic health data is initialized by using the regular physical examination data.
The execution main body of the heart state monitoring method provided by the embodiment of the invention can be a cloud server, the cloud server is a simple, efficient, safe and reliable computing service with elastically stretchable processing capacity, the management mode is simpler and more efficient than that of a physical server, and a user can quickly create or release any plurality of servers without purchasing hardware in advance. The cloud server helps to quickly construct a more stable and safe application, and the difficulty of developing operation and maintenance and the overall IT cost are reduced. In the embodiment of the invention, the cloud server is not only used for constructing and updating the digital heart, but also used for analyzing and mining the data of the basic health data, and meanwhile, the cloud server is also responsible for the safety maintenance of all information related to the patient.
After obtaining the basic health data, the cloud server may update the patient's cardiac state monitoring data based on the basic health data and the motion state of the digital heart. Based on the heart state monitoring data of the patient, the heart state of the patient can be dynamically monitored in real time, the physical condition of the patient can be monitored in real time, meanwhile, the influence factors of the change of the heart state of the patient can be analyzed by referring to the basic health data of the patient, and then a doctor is assisted to provide a rehabilitation suggestion.
According to any of the above embodiments, the method for monitoring cardiac state further comprises:
and if a heart state monitoring data query request sent by the client is received, returning the heart state monitoring data corresponding to the patient to the heart state monitoring data query request.
Specifically, when the user needs to know the cardiac state monitoring data of the patient, the application client may send a cardiac state monitoring data query request to the cloud server. After receiving the cardiac state monitoring data query request sent by the client, the cloud server sends cardiac state monitoring data of the patient corresponding to the cardiac state monitoring data query request to the client. The user can inquire the heart state monitoring data of the patient at any time through the client, and the user can be the patient himself or an attending doctor of the patient, and the like. The client may be a mobile phone, a tablet, a computer, or the like, which is not specifically limited in this embodiment of the present invention.
Based on any of the above embodiments, fig. 2 is a schematic structural diagram of a cardiac state monitoring system according to an embodiment of the present invention, and as shown in fig. 2, the cardiac state monitoring system according to the embodiment of the present invention includes:
a data acquisition module 210 for acquiring real-time cardiac data of a patient;
a digital heart update module 220 for synchronizing a pre-constructed motion state of the digital heart of the patient based on the real-time cardiac data;
wherein the digital heart comprises a base three-dimensional model of the heart constructed based on the patient's thoracic CT data and a three-dimensional model of the coronary artery constructed based on the patient's coronary angiography data.
According to the heart state monitoring system provided by the embodiment of the invention, the basic heart three-dimensional model is constructed based on the chest CT data, the coronary artery three-dimensional model is constructed based on the coronary angiography data, the basic heart three-dimensional model and the coronary artery three-dimensional model are combined to construct the digital heart, and the digital twin system between the human heart and the simulation model is established, so that the dynamic visualization of the human heart is realized, the heart state of a patient can be clearly and intuitively known conveniently, meanwhile, the motion state of the digital heart is synchronously updated based on the real-time heart data, and the real-time monitoring of the heart state is realized.
In accordance with any of the above embodiments, the cardiac condition monitoring system further comprises:
the digital heart construction module is used for inputting the chest CT data into a basic heart three-dimensional reconstruction network to obtain a basic heart three-dimensional model output by the basic heart three-dimensional reconstruction network;
inputting the coronary angiography data into a coronary three-dimensional reconstruction network to obtain the coronary three-dimensional model output by the basic heart three-dimensional reconstruction network;
wherein the basic cardiac three-dimensional reconstruction network is trained based on sample chest CT data and a sample basic cardiac three-dimensional model, the coronary three-dimensional reconstruction network is trained based on sample coronary angiography data and a sample coronary three-dimensional model, and the sample coronary three-dimensional model is determined based on sample coronary CTA data.
According to the heart state monitoring system provided by the embodiment of the invention, the digital heart is constructed through the basic heart three-dimensional reconstruction network and the coronary three-dimensional reconstruction network, the coronary three-dimensional reconstruction network is trained by using a weak supervised learning method, the construction of the coronary three-dimensional reconstruction network can be realized when a large number of training sets cannot be obtained, and meanwhile, the precision of the coronary three-dimensional reconstruction network is ensured.
According to any of the above embodiments, the cardiac condition monitoring system further comprises:
a digital cardiac motion initialization module for initializing the heart beats of the basic three-dimensional model of the heart based on a basic electrocardiogram of the patient;
initializing coronary vessel motion of the three-dimensional model of coronary vessels based on the patient's coronary angiography video.
According to the heart state monitoring system provided by the embodiment of the invention, the heart beating of the basic heart three-dimensional model is initialized based on the basic electrocardiogram of the patient, and the coronary vessel motion of the coronary artery three-dimensional model is initialized based on the coronary angiography video of the patient, so that the dynamic visualization of the human heart is realized, and the heart state of the patient can be conveniently and visually known.
In accordance with any of the above embodiments, the cardiac condition monitoring system further comprises:
a preprocessing module for preprocessing the chest CT data and the coronary angiography data;
wherein the pre-processing comprises image de-noising and/or image enhancement.
The heart state monitoring system provided by the embodiment of the invention eliminates noise information by preprocessing the chest CT data and the coronary angiography data, simultaneously reserves and highlights the image characteristics of the heart and the coronary vessels, and is favorable for constructing a basic heart three-dimensional model and a coronary three-dimensional model by performing image segmentation based on the chest CT data and the coronary angiography data.
In accordance with any of the above embodiments, the cardiac condition monitoring system further comprises:
a basic health data acquisition module for acquiring basic health data of the patient;
a monitoring data update module for updating the cardiac status monitoring data of the patient based on the basic health data of the patient and the motion status of the digital heart of the patient.
In accordance with any of the above embodiments, the cardiac condition monitoring system further comprises:
and the data sending module is used for returning the cardiac state monitoring data of the patient corresponding to the cardiac state monitoring data query request if the cardiac state monitoring data query request sent by the client is received.
Fig. 3 is a schematic entity structure diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 3, the electronic device may include: the system comprises a processor 301, a communication interface 302, a memory 303 and a communication bus 304, wherein the processor 301, the communication interface 302 and the memory 303 are communicated with each other through the communication bus 304. Processor 301 may call logic instructions in memory 303 to perform the following method: acquiring real-time cardiac data of a patient; synchronizing a pre-constructed motion state of the digital heart of the patient based on the real-time cardiac data; the digital heart comprises a basic heart three-dimensional model and a coronary artery three-dimensional model, wherein the basic heart three-dimensional model is constructed on the basis of chest CT data of a patient, and the coronary artery three-dimensional model is constructed on the basis of coronary angiography data of the patient.
In addition, the logic instructions in the memory 303 may be implemented in the form of software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention or a part thereof which substantially contributes to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented by a processor to perform the method provided by the foregoing embodiments, for example, including: acquiring real-time cardiac data of a patient; synchronizing a pre-constructed motion state of the digital heart of the patient based on the real-time cardiac data; the digital heart comprises a basic heart three-dimensional model and a coronary artery three-dimensional model, wherein the basic heart three-dimensional model is constructed on the basis of chest CT data of a patient, and the coronary artery three-dimensional model is constructed on the basis of coronary angiography data of the patient.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (7)
1. A method of cardiac condition monitoring, comprising:
acquiring real-time cardiac data of a patient;
synchronizing a pre-constructed motion state of the patient's digital heart based on the real-time cardiac data;
acquiring basic health data of the patient;
updating cardiac state monitoring data of the patient based on the basic health data of the patient and the motion state of the digital heart of the patient;
wherein the digital heart comprises a base three-dimensional model of the heart constructed based on thoracic CT data of the patient and a three-dimensional model of the coronary artery constructed based on coronary angiography data of the patient;
the construction method of the digital heart specifically comprises the following steps:
inputting the chest CT data into a basic heart three-dimensional reconstruction network to obtain a basic heart three-dimensional model output by the basic heart three-dimensional reconstruction network;
inputting the coronary angiography data into a coronary three-dimensional reconstruction network to obtain the coronary three-dimensional model output by the coronary three-dimensional reconstruction network;
wherein the basic cardiac three-dimensional reconstruction network is trained based on sample chest CT data and a sample basic cardiac three-dimensional model, the coronary three-dimensional reconstruction network is trained based on sample coronary angiography data and a sample coronary three-dimensional model, and the sample coronary three-dimensional model is determined based on sample coronary CTA data;
the training of the coronary artery three-dimensional reconstruction network adopts a weak supervision learning method, namely, sample coronary artery CTA data and sample coronary artery angiography data which are used for determining a sample coronary artery three-dimensional model do not belong to the same patient.
2. A cardiac condition monitoring method as set forth in claim 1, wherein synchronizing the pre-constructed motion state of the digital heart of the patient based on the real-time cardiac data further comprises:
initializing a heart beat of the basic heart three-dimensional model based on a basic electrocardiogram of the patient;
initializing coronary vessel motion of the three-dimensional model of coronary vessels based on the patient's coronary angiography video.
3. A cardiac condition monitoring method as set forth in any of claims 1-2, further including, prior to the acquiring real-time cardiac data of a patient:
preprocessing the thoracic CT data and the coronary angiography data;
wherein the pre-processing comprises image de-noising and/or image enhancement.
4. The cardiac condition monitoring method of claim 1, further comprising:
and if a heart state monitoring data query request sent by the client is received, returning the heart state monitoring data of the patient corresponding to the heart state monitoring data query request.
5. A cardiac condition monitoring system, comprising:
the data acquisition module is used for acquiring real-time cardiac data of a patient;
a digital heart update module for synchronizing a pre-constructed motion state of the patient's digital heart based on the real-time cardiac data;
a basic health data acquisition module for acquiring basic health data of the patient;
a monitoring data updating module for updating the patient's cardiac state monitoring data based on the patient's basic health data and the patient's digital cardiac motion state;
wherein the digital heart comprises a base three-dimensional model of the heart constructed based on thoracic CT data of the patient and a three-dimensional model of the coronary artery constructed based on coronary angiography data of the patient;
the construction method of the digital heart specifically comprises the following steps:
inputting the chest CT data into a basic heart three-dimensional reconstruction network to obtain a basic heart three-dimensional model output by the basic heart three-dimensional reconstruction network;
inputting the coronary angiography data into a coronary three-dimensional reconstruction network to obtain the coronary three-dimensional model output by the coronary three-dimensional reconstruction network;
wherein the basic cardiac three-dimensional reconstruction network is trained based on sample chest CT data and a sample basic cardiac three-dimensional model, the coronary three-dimensional reconstruction network is trained based on sample coronary angiography data and a sample coronary three-dimensional model, and the sample coronary three-dimensional model is determined based on sample coronary CTA data;
the training of the coronary artery three-dimensional reconstruction network adopts a weak supervision learning method, namely, sample coronary artery CTA data and sample coronary artery angiography data which are used for determining a sample coronary artery three-dimensional model do not belong to the same patient.
6. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor, when executing the program, carries out the steps of the method of cardiac condition monitoring according to any one of claims 1 to 4.
7. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the cardiac state monitoring method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010421667.4A CN111755104B (en) | 2020-05-18 | 2020-05-18 | Heart state monitoring method and system, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010421667.4A CN111755104B (en) | 2020-05-18 | 2020-05-18 | Heart state monitoring method and system, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111755104A CN111755104A (en) | 2020-10-09 |
| CN111755104B true CN111755104B (en) | 2022-11-01 |
Family
ID=72673440
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010421667.4A Active CN111755104B (en) | 2020-05-18 | 2020-05-18 | Heart state monitoring method and system, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111755104B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115206551A (en) * | 2022-08-10 | 2022-10-18 | 北京京东拓先科技有限公司 | Health state monitoring method and device based on digital twins |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201965829U (en) * | 2010-12-30 | 2011-09-07 | 孙英贤 | External heart model device |
| CN103270513A (en) * | 2010-08-12 | 2013-08-28 | 哈特弗罗公司 | Method and system for patient-pecific modeling of blood flow |
| CN103489360A (en) * | 2012-06-12 | 2014-01-01 | 韦伯斯特生物官能(以色列)有限公司 | Physical heart simulator |
| CN105105775A (en) * | 2011-07-19 | 2015-12-02 | 株式会社东芝 | Myocardial motion analysis device |
| CN110555261A (en) * | 2019-08-29 | 2019-12-10 | 清华大学 | Digital three-generation simulation method and device for heart motion |
-
2020
- 2020-05-18 CN CN202010421667.4A patent/CN111755104B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103270513A (en) * | 2010-08-12 | 2013-08-28 | 哈特弗罗公司 | Method and system for patient-pecific modeling of blood flow |
| CN201965829U (en) * | 2010-12-30 | 2011-09-07 | 孙英贤 | External heart model device |
| CN105105775A (en) * | 2011-07-19 | 2015-12-02 | 株式会社东芝 | Myocardial motion analysis device |
| CN103489360A (en) * | 2012-06-12 | 2014-01-01 | 韦伯斯特生物官能(以色列)有限公司 | Physical heart simulator |
| CN110555261A (en) * | 2019-08-29 | 2019-12-10 | 清华大学 | Digital three-generation simulation method and device for heart motion |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111755104A (en) | 2020-10-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210335497A1 (en) | Systems and methods for image processing to determine blood flow | |
| CN108830848B (en) | Device and system for determining a sequence of vessel condition parameters on a vessel using a computer | |
| CN108511075B (en) | Method and system for non-invasively acquiring fractional flow reserve | |
| US20210022616A1 (en) | Method and system for visualization of heart tissue at risk | |
| JP6918794B2 (en) | Anatomical modeling system and how it works | |
| AU2013331213B2 (en) | Systems and methods for numerically evaluating vasculature | |
| EP3277169B1 (en) | Systems and methods for estimating virtual perfusion images | |
| CN107092771A (en) | The personalized model integrated using periodic data | |
| US11468570B2 (en) | Method and system for acquiring status of strain and stress of a vessel wall | |
| CN107665737A (en) | Vascular wall stress-strain state acquisition methods, computer-readable medium and system | |
| CN114010157A (en) | Blood vessel plaque risk prediction method, device, equipment and medium | |
| Revathi et al. | An intelligent model for coronary heart disease diagnosis | |
| CN111755104B (en) | Heart state monitoring method and system, electronic equipment and storage medium | |
| CN112862827B (en) | Method, device, terminal and storage medium for determining opening parameters of left atrial appendage | |
| Waris et al. | Prediction of heart conditions by consensus K-nearest neighbor algorithm and convolution neural network | |
| KR20240009348A (en) | Method, program and apparatus for providing visualization contents based on electrocardiogram interpreting | |
| CN113838007A (en) | Physiological parameter acquisition method and device, electronic equipment and storage medium | |
| KR20240009349A (en) | Method, program and apparatus for providing visualization contents based on electrocardiogram interpreting | |
| Rudnicka et al. | Advancements in artificial intelligence-driven techniques for interventional cardiology | |
| WO2024002766A1 (en) | Hyper-personalized treatment based on coronary motion fields and big data | |
| WO2022266291A1 (en) | Synthetic echo from ecg |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |