CN111180075A - Dynamic model established based on heart murmur and computer simulation method - Google Patents
Dynamic model established based on heart murmur and computer simulation method Download PDFInfo
- Publication number
- CN111180075A CN111180075A CN202010136356.3A CN202010136356A CN111180075A CN 111180075 A CN111180075 A CN 111180075A CN 202010136356 A CN202010136356 A CN 202010136356A CN 111180075 A CN111180075 A CN 111180075A
- Authority
- CN
- China
- Prior art keywords
- heart
- data
- computer simulation
- model
- cardiac
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
Abstract
The invention discloses a dynamic model established based on heart murmurs and a computer simulation method, and belongs to the technical field of medical treatment. A dynamics model established based on heart murmurs and a computer simulation method synchronously acquire heart sounds, electrocardio and echocardiogram data, establish a hemodynamic model through computer simulation software, utilize diagnosis results of heart ultrasound as data labels, perform feature extraction on heart murmurs related to heart diseases through a machine learning algorithm to obtain time domain and frequency domain feature parameters after quantification of the heart murs, finally, simulate pure heart murs through the established heart disease hemodynamic model by building an in-vitro cardiac disease hemodynamic model experiment system, perform contrast analysis on actual heart murs after feature extraction, verify whether the heart murs after feature extraction accurately show objective conditions, and summarize the quantification standard of the heart murmurs of heart diseases.
Description
Technical Field
The invention relates to the technical field of medical treatment, in particular to a dynamic model established based on heart murmurs and a method for computer simulation.
Background
Congenital heart disease (hereinafter referred to as congenital heart disease) is up to 8.98 per thousand of the incidence rate of newborn infants in China, and is the primary factor threatening the health of children. The heart sound auscultation is mainly used for screening the congenital heart disease, more than two levels of heart murmurs are used as a judgment basis, and the heart color ultrasound is used for determining the congenital heart disease.
Heart murmurs are an important basis for screening and diagnosing heart diseases firstly, but the auscultation by doctors commonly adopted at present is a traditional stethoscope, the collected heart sound data cannot be stored in a digital mode, the heart sounds can only be judged by the doctors according to own experiences, the heart murs can only be judged according to artificial qualitative basis, quantitative judgment parameters and basis are lacked, so that the heart murs are not quantitatively unified, and therefore the relevant standard research of the heart murs is based on qualitative and non-digital, so that the misdiagnosis rate and missed diagnosis rate of the primary screening of the heart diseases are too high, and the children with the heart diseases cannot be treated accurately in time.
With the development of digital diagnosis and treatment technology, digital stethoscopes have been gradually applied to domestic hospitals, especially pediatric hospitals and pediatric consulting rooms with huge auscultation. The auscultation diagnosis of the doctor can be assisted by artificial intelligence through the digitized heart sounds. However, the machine learning algorithm commonly used in artificial intelligence at present is a black box process, which is a feature extraction realized according to a statistical rule, and lacks effective cardiac hemodynamics verification, so that the identified feature parameters related to cardiac noise are not evidence-based in an effective experimental mode.
Disclosure of Invention
1. Technical problem to be solved
Aiming at the problems in the prior art, the invention aims to provide a dynamic model established based on heart murmurs and a computer simulation method, which can simulate pure heart murs through the established heart disease hemodynamics model, carry out comparison analysis through the actual heart murs after characteristic extraction, verify whether the heart murs after characteristic extraction accurately show objective conditions, and summarize the quantitative standard of the heart murmurs of heart disease.
2. Technical scheme
In order to solve the above problems, the present invention adopts the following technical solutions.
A method for establishing a dynamic model and computer simulation based on heart murmurs comprises the following steps:
the method comprises the following steps of firstly, synchronously acquiring heart sound, electrocardio and echocardiogram data for suspected children with the congenital heart disease;
secondly, establishing a hemodynamic model through computer simulation software on the basis of the echocardiogram data in the first step, and marking by using the diagnosis result of the cardiac ultrasound as data;
thirdly, extracting the characteristics of heart murmurs related to the heart disease through a machine learning algorithm to obtain characteristic parameters of time domains and frequency domains after the heart murs are quantized;
step four, establishing an in vitro model experiment system of the hemodynamics of the congenital heart disease on the basis of the step one and the step two for verification;
and step five, verifying whether the characteristic parameters of the heart murmurs extracted by the machine learning algorithm are in accordance with the experimental results in the step four, and taking the verified characteristic parameters as the basis of the heart mur quantization standard.
Furthermore, the phonocardiogram data and the electrocardiogram data are collected while the echocardiogram data are collected in the first step, and the collected phonocardiogram data and the electrocardiogram data are subjected to data preprocessing, so that the subsequent feature extraction operation is more convenient by preprocessing the collected phonocardiogram data and the electrocardiogram data, and the feature extraction operation is accurately and efficiently carried out.
Further, the echocardiogram data comprises M-type echocardiogram, two-dimensional echocardiogram, frequency spectrum Doppler measurement, normal pulmonary artery pressure and division and grading of pulmonary artery high pressure, the M-type echocardiogram data comprises aorta internal diameter, left atrium internal diameter, left ventricle diastolic internal diameter and left ventricle systolic internal diameter, the method comprises the steps of collecting data such as right ventricular internal diameter and pulmonary artery internal diameter, collecting data such as a parasternal left ventricular long axis section, a parasternal bottom short axis section, a four-chamber heart section at the apex of the heart and two-chamber section measurement at the apex of the heart, collecting data such as mitral valve orifice blood flow, tricuspid valve orifice blood flow and aortic valve orifice blood flow in a two-dimensional echocardiogram, dividing and classifying normal pulmonary artery pressure and pulmonary artery high pressure, and collecting data such as normal pulmonary artery pressure (at rest), pulmonary artery high pressure and pulmonary artery high pressure (PASP) in a classification mode.
Furthermore, in the first step, a seven-step screening method is adopted to collect an echocardiogram of the infant patient, record relevant parameters such as a heart structure and ultrasonic spectrum Doppler, and collect data of the relevant parameters, so that the dynamic state of the heart can be simulated by computer simulation software, and the simulation effect is better.
Further, the computer simulation in the second step includes a heart simulation modeling, an electrocardiogram data importing and a phonocardiogram data importing, the heart simulation modeling is data (blood vessel size, size of atrium and ventricle, wall thickness, defect position and size, etc.) in the heart structure collected by the ultrasonic device and a hemodynamics value measured by doppler, the heart simulation modeling is performed by using computer simulation software, dynamic simulation is established on a time series according to different data of diastole and systole, the electrocardiogram data importing is electrocardiogram data according to the time series, the related electrocardiogram data can be checked in the heart dynamic simulation process, the phonocardiogram data importing is phonocardiogram data synchronously, the dynamic heart model based on the echocardiogram and the electrocardiogram are played synchronously on the same time axis, the characteristics of the heart murmurmurs obtained by machine learning change according to the hemodynamics value, establishing the hemodynamic relationship between the two.
Furthermore, the hemodynamic model of the echocardiography data is based on a fluid-solid-physiological phenomenon coupling analysis technology, various normal and pathological heart and blood vessel models with real structures are manufactured by adopting transparent silicon rubber through a reverse engineering technology, blood flow characteristics are observed in vitro by utilizing a PIV visualization technology, and the effectiveness of numerical simulation is verified.
Furthermore, the in vitro model in the in vitro model experiment system comprises four sets of congenital heart disease types including ventricular septal defect, patent ductus arteriosus, atrial septal defect and pulmonary valve stenosis, wherein the four sets of congenital heart disease types are the four most common types of congenital heart disease.
Furthermore, the in vitro model experiment system is a heart model with corresponding ventricular septal defect and room defect printed by using soft rubber 3D according to the statistical data rule of cardiac ultrasound, blood vessels and valves are printed according to the patent ductus arteriosus and the stenosis condition of the pulmonary valve 3D, the flow rate and the pressure in the concerned area are controlled by the artificial heart pump, the audio generated by the model is recorded by arranging a heart sound sensor in the concerned area, the collected audio in the concerned area is compared with the actually collected heart sound of the patient, referring to the right diagram in fig. 3, the actually collected heart sound has more noise due to the influence of other factors in the thoracic cavity, the characteristic value of the heart murmurmur is obtained through machine learning, and the characteristic value is obtained through the statistical rule and is a process of a black box.
Furthermore, the corresponding relation between the data for evaluating the heart state, which are synchronously acquired by the ultrasonic data, the phonocardiogram data and the electrocardiogram data, and the four sets of antecedent heart disease typing is established through the computer simulation software (which is independently developed), so that the disease type corresponding to the sick child can be judged, and the computer simulation software is effective for the disease state according to the statistical display of the data.
3. Advantageous effects
Compared with the prior art, the invention has the advantages that:
(1) according to the scheme, pure heart murmurs can be simulated through the established heart disease hemodynamics model, comparison analysis is carried out on the actual heart murs after characteristic extraction, whether the heart murs after characteristic extraction accurately show objective conditions is verified, and the quantitative standard of the heart murs of the heart disease is summarized.
(2) And acquiring phonocardiogram data and electrocardiogram data while acquiring the ultrasonic cardiogram data in the step one, and performing data preprocessing on the acquired phonocardiogram data and the acquired electrocardiogram data, wherein the preprocessing operation on the acquired phonocardiogram data and the acquired electrocardiogram data can make the subsequent feature extraction operation more convenient, and the feature extraction operation is accurate and efficient.
(3) The echocardiogram data comprises M-type echocardiogram, two-dimensional echocardiogram, frequency spectrum Doppler measurement, normal pulmonary artery pressure and division and grading of pulmonary artery high pressure, the M-type echocardiogram data comprises aorta internal diameter, left atrium internal diameter, left ventricle end-diastolic internal diameter and left ventricle end-systolic internal diameter, the method comprises the steps of collecting data such as right ventricular internal diameter and pulmonary artery internal diameter, collecting data such as a parasternal left ventricular long axis section, a parasternal bottom short axis section, a four-chamber heart section at the apex of the heart and two-chamber section measurement at the apex of the heart, collecting data such as mitral valve orifice blood flow, tricuspid valve orifice blood flow and aortic valve orifice blood flow in a two-dimensional echocardiogram, dividing and classifying normal pulmonary artery pressure and pulmonary artery high pressure, and collecting data such as normal pulmonary artery pressure (at rest), pulmonary artery high pressure and pulmonary artery high pressure (PASP) in a classification mode.
(4) In the first step, a seven-step screening method is adopted to collect an echocardiogram of the infant patient, record relevant parameters such as a heart structure and ultrasonic spectrum Doppler and the like, collect relevant parameter data, and simulate the dynamic state of the heart through computer simulation software, so that the simulation effect is better.
(5) In the second step, computer simulation comprises heart simulation modeling, electrocardiogram data importing and phonocardiogram data importing, wherein the heart simulation modeling is data (blood vessel size, size of atrium and ventricle, wall thickness, defect position and size and the like) on the aspect of heart structure acquired by ultrasonic equipment and a hemodynamic value measured by Doppler, computer simulation software is used for performing simulation modeling on the heart, dynamic simulation is established on a time sequence according to different data of diastole and systole, the electrocardiogram data importing is electrocardiogram data according to the time sequence, related electrocardiogram data can be checked in the heart dynamic simulation process, the phonocardiogram data importing is phonocardiogram data synchronously importing, a dynamic heart model based on the echocardiogram and the electrocardiogram are synchronously played on the same time axis, the characteristics of heart murmurmurs acquired through machine learning change according to the hemodynamic value, establishing the hemodynamic relationship between the two.
(6) The hemodynamics model of the echocardiography data is characterized in that on the basis of a fluid-solid-physiological phenomenon coupling analysis technology, various normal and pathological heart and blood vessel models with real structures are manufactured by adopting transparent silicon rubber through a reverse engineering technology, the blood flow characteristics are observed in vitro by utilizing a PIV visualization technology, and the effectiveness of numerical simulation is verified.
(7) The in vitro model in the in vitro model experiment system comprises four sets of congenital heart disease types including ventricular septal defect, patent ductus arteriosus, atrial septal defect and pulmonary valve stenosis, wherein the four sets of congenital heart disease types are the four most common types of congenital heart disease.
(8) The in-vitro model experiment system is a heart model with ventricular septal defect and ventricular lacuna defect printed by soft rubber 3D according to the statistical data rule of cardiac ultrasound, blood vessels and valves are printed according to the patent condition of an arterial duct and the stenosis condition of a pulmonary valve 3D, the flow rate and the pressure in an attention area are controlled by an artificial heart pump, a heart sound sensor is arranged in the attention area to record the audio frequency generated by the model, the acquired audio frequency in the attention area is compared with the heart sound of a patient actually acquired, the right image in the image 3 is referred, the heart sound actually acquired is influenced by other factors in the thoracic cavity, the existing noise is more, the characteristic value of the heart murmur is acquired through machine learning, the characteristic value is acquired through the statistical rule, and the process is a black box.
(9) The corresponding relation between the data for evaluating the heart state synchronously acquired by the ultrasonic data, the phonocardiogram data and the electrocardiogram data and four sets of antecedent heart disease typing is established through computer simulation software (independently developed), the disease type corresponding to the child patient can be judged, and then the disease condition can be effectively displayed according to data statistics.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a schematic diagram of an in vitro model experiment system according to the present invention;
FIG. 3 is a schematic diagram of a comparative analysis structure of the heart murmurs simulated by the in vitro model and the real heart murs according to the present invention.
Detailed Description
Please refer to fig. 1-3, which is a method for dynamic model and computer simulation based on cardiac noise, which uses an algorithm to research the quantitative relationship of cardiac noise, and comprises the following steps:
the method comprises the following steps that firstly, heart sound, electrocardio and echocardiogram data are synchronously collected for children suspected to be sick with a heart disease (the heart is the power for pushing blood circulation, the rhythmic contraction and relaxation of the heart and the unidirectional flow guide of heart valves, the action of a power pump of the heart in the blood circulation is ensured, the physiological function of the heart comprises multi-scale and multi-physical processes from a myocardial subcellular excitation contraction mechanism to the hemodynamics and structural mechanics at an organ level, and the correlation of the structure and the function of the heart can be better analyzed by establishing a heart hemodynamics model based on the synchronously collected heart sound, electrocardio and echocardiogram data);
secondly, establishing a hemodynamic model through computer simulation software on the basis of the echocardiogram data in the first step, and marking by using the diagnosis result of the cardiac ultrasound as data;
thirdly, extracting the characteristics of heart murmurs related to the heart disease through a machine learning algorithm to obtain characteristic parameters of time domains and frequency domains after the heart murs are quantized;
step four, establishing an in vitro model experiment system of the hemodynamics of the congenital heart disease on the basis of the step one and the step two for verification;
and step five, verifying whether the characteristic parameters of the heart murmurs extracted by the machine learning algorithm are in accordance with the experimental results in the step four, and taking the verified characteristic parameters as the basis of the heart mur quantization standard.
And acquiring phonocardiogram data and electrocardiogram data while acquiring the ultrasonic cardiogram data in the step one, and performing data preprocessing on the acquired phonocardiogram data and the acquired electrocardiogram data, wherein the preprocessing operation on the acquired phonocardiogram data and the acquired electrocardiogram data can make the subsequent feature extraction operation more convenient, and the feature extraction operation is accurate and efficient.
The echocardiogram data comprises M-type echocardiogram, two-dimensional echocardiogram, frequency spectrum Doppler measurement, normal pulmonary artery pressure and division and grading of pulmonary artery high pressure, the M-type echocardiogram data comprises aorta internal diameter, left atrium internal diameter, left ventricle end-diastolic internal diameter and left ventricle end-systolic internal diameter, the method comprises the steps of collecting data such as right ventricular internal diameter and pulmonary artery internal diameter, collecting data such as a parasternal left ventricular long axis section, a parasternal bottom short axis section, a four-chamber heart section at the apex of the heart and two-chamber section measurement at the apex of the heart, collecting data such as mitral valve orifice blood flow, tricuspid valve orifice blood flow and aortic valve orifice blood flow in a two-dimensional echocardiogram, dividing and classifying normal pulmonary artery pressure and pulmonary artery high pressure, and collecting data such as normal pulmonary artery pressure (at rest), pulmonary artery high pressure and pulmonary artery high pressure (PASP) in a classification mode.
In the first step, a seven-step screening method (which is a known technology of technicians in the field) is adopted to acquire an echocardiogram of the infant patient, relevant parameters such as a heart structure and ultrasonic spectrum Doppler are recorded, relevant parameter data are acquired, the dynamic state of the heart can be simulated through computer simulation software, and the simulation effect is better.
In the second step, computer simulation comprises heart simulation modeling, electrocardiogram data importing and phonocardiogram data importing, wherein the heart simulation modeling is data (blood vessel size, size of atrium and ventricle, wall thickness, defect position and size and the like) on the aspect of heart structure acquired by ultrasonic equipment and a hemodynamic value measured by Doppler, computer simulation software is used for performing simulation modeling on the heart, dynamic simulation is established on a time sequence according to different data of diastole and systole, the electrocardiogram data importing is electrocardiogram data according to the time sequence, related electrocardiogram data can be checked in the heart dynamic simulation process, the phonocardiogram data importing is phonocardiogram data synchronously importing, a dynamic heart model based on the echocardiogram and the electrocardiogram are synchronously played on the same time axis, the characteristics of heart murmurmurs acquired through machine learning change according to the hemodynamic value, establishing the hemodynamic relationship between the two.
The hemodynamics model of the echocardiography data is characterized in that on the basis of a fluid-solid-physiological phenomenon coupling analysis technology, various normal and pathological heart and blood vessel models with real structures are manufactured by adopting transparent silicon rubber through a reverse engineering technology, the blood flow characteristics are observed in vitro by utilizing a PIV visualization technology, and the effectiveness of numerical simulation is verified.
The in vitro model in the in vitro model experiment system comprises four sets of congenital heart disease types including ventricular septal defect, patent ductus arteriosus, atrial septal defect and pulmonary valve stenosis, wherein the four sets of congenital heart disease types are the four most common types of congenital heart disease.
The in-vitro model experiment system is a heart model with ventricular septal defect and ventricular lacuna defect printed by soft rubber 3D according to the statistical data rule of cardiac ultrasound, blood vessels and valves are printed according to the patent condition of an arterial duct and the stenosis condition of a pulmonary valve 3D, the flow rate and the pressure in an attention area are controlled by an artificial heart pump, a heart sound sensor is arranged in the attention area to record the audio frequency generated by the model, the acquired audio frequency in the attention area is compared with the heart sound of a patient actually acquired, the right image in the image 3 is referred, the heart sound actually acquired is influenced by other factors in the thoracic cavity, the existing noise is more, the characteristic value of the heart murmur is acquired through machine learning, the characteristic value is acquired through the statistical rule, and the process is a black box.
The corresponding relation between the data for evaluating the heart state synchronously acquired by the ultrasonic data, the phonocardiogram data and the electrocardiogram data and four sets of antecedent heart disease typing is established through computer simulation software (independently developed), the disease type corresponding to the child patient can be judged, and then the disease condition can be effectively displayed according to data statistics.
The heart sound signal, the electrocardiosignal and the heart ultrasonic image are synchronously digitally collected for the first time, a hemodynamics model related to heart murmurs is established through computer simulation, pure heart murmurs can be simulated through the established heart disease hemodynamics model, comparison analysis is carried out on the actual heart murs after characteristic extraction, whether the heart murs after characteristic extraction accurately show objective conditions is verified, the quantitative standard of the heart murmurs of heart disease is summarized, the mathematical model after quantitative analysis is applied to artificial intelligence assisted auscultation, and the great effect of digital auscultation in early screening of heart disease is exerted.
The above; but are merely preferred embodiments of the invention; the scope of the invention is not limited thereto; any person skilled in the art is within the technical scope of the present disclosure; the technical scheme and the improved concept of the invention are equally replaced or changed; are intended to be covered by the scope of the present invention.
Claims (9)
1. A dynamic model established based on heart murmurs and a computer simulation method are characterized in that: the method comprises the following steps:
the method comprises the following steps of firstly, synchronously acquiring heart sound, electrocardio and echocardiogram data for suspected children with the congenital heart disease;
secondly, establishing a hemodynamic model through computer simulation software on the basis of the echocardiogram data in the first step, and marking by using the diagnosis result of the cardiac ultrasound as data;
thirdly, extracting the characteristics of heart murmurs related to the heart disease through a machine learning algorithm to obtain characteristic parameters of time domains and frequency domains after the heart murs are quantized;
step four, establishing an in vitro model experiment system of the hemodynamics of the congenital heart disease on the basis of the step one and the step two for verification;
and step five, verifying whether the characteristic parameters of the heart murmurs extracted by the machine learning algorithm are in accordance with the experimental results in the step four, and taking the verified characteristic parameters as the basis of the heart mur quantization standard.
2. The method for cardiac mur-based dynamical model and computer simulation of claim 1, wherein: and in the first step, the ultrasonic cardiogram data is collected, the phonocardiogram data and the electrocardiogram data are collected, and the collected phonocardiogram data and the electrocardiogram data are subjected to data preprocessing.
3. The method for cardiac mur-based dynamical model and computer simulation of claim 1, wherein: the echocardiogram data includes M-mode echocardiogram, two-dimensional echocardiogram, frequency spectrum Doppler measurement, normal pulmonary artery pressure, and division and grading of pulmonary artery high pressure.
4. A method for dynamic modeling and computer simulation based on cardiac murmurs, as claimed in claim 3, wherein: in the first step, a seven-step screening method is adopted to acquire an echocardiogram of the infant patient and record relevant parameters such as a heart structure, ultrasonic spectrum Doppler and the like.
5. The method for cardiac mur-based dynamical model and computer simulation of claim 1, wherein: and the computer simulation in the second step comprises heart simulation modeling, electrocardiogram data import and phonocardiogram data import.
6. The method for cardiac mur-based dynamical model and computer simulation of claim 1, wherein: the hemodynamics model of the echocardiography data is characterized in that on the basis of a fluid-solid-physiological phenomenon coupling analysis technology, various normal and pathological heart and blood vessel models with real structures are manufactured by adopting transparent silicon rubber through a reverse engineering technology, and the blood flow characteristics are observed in vitro by utilizing a PIV visualization technology to verify the effectiveness of numerical simulation.
7. The method for cardiac mur-based dynamical model and computer simulation of claim 1, wherein: the in vitro model in the in vitro model experiment system comprises four sets of congenital heart disease types including ventricular septal defect, patent ductus arteriosus, atrial septal defect and pulmonary stenosis.
8. The method for cardiac mur-based dynamical model and computer simulation of claim 7, wherein: the in-vitro model experiment system is characterized in that a heart model with ventricular septal defect and ventricular lacuna defect is printed by soft gum in a 3D mode according to the statistical data rule of heart ultrasound, blood vessels and valves are printed in a 3D mode according to the situation that an arterial duct is not closed and a pulmonary valve is narrow, the flow speed and the pressure of an attention area are controlled through an artificial heart pump, a heart sound sensor is arranged in the attention area, and audio generated by the model is recorded.
9. The method for cardiac mur-based dynamical model and computer simulation of claim 7, wherein: and establishing the corresponding relation between the data for evaluating the heart state, which are synchronously acquired by the ultrasonic data, the phonocardiogram data and the electrocardiogram data, and the four sets of congenital heart disease typing through the computer simulation software.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010136356.3A CN111180075B (en) | 2020-03-02 | 2020-03-02 | Dynamics model established based on heart murmur and computer simulation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010136356.3A CN111180075B (en) | 2020-03-02 | 2020-03-02 | Dynamics model established based on heart murmur and computer simulation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111180075A true CN111180075A (en) | 2020-05-19 |
| CN111180075B CN111180075B (en) | 2023-10-20 |
Family
ID=70658401
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010136356.3A Active CN111180075B (en) | 2020-03-02 | 2020-03-02 | Dynamics model established based on heart murmur and computer simulation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111180075B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117577301A (en) * | 2023-11-20 | 2024-02-20 | 四川大学华西医院 | Outside-hospital emergency system for automatic identification and intelligent auxiliary decision-making of cardiac arrest |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4905706A (en) * | 1988-04-20 | 1990-03-06 | Nippon Colin Co., Ltd. | Method an apparatus for detection of heart disease |
| US20030093003A1 (en) * | 1999-09-29 | 2003-05-15 | Raymond Watrous | Multi-modal cardiac diagnostic decision support system and method |
| CN101916333A (en) * | 2010-08-12 | 2010-12-15 | 四川大学华西医院 | Transesophageal echocardiography visual simulation system and method |
| CN105474219A (en) * | 2013-08-28 | 2016-04-06 | 西门子公司 | Systems and methods for estimating physiological heart measurements from medical images and clinical data |
| CN107348971A (en) * | 2017-08-17 | 2017-11-17 | 上海交通大学 | A kind of heart disease screening system based on heart sound detection and machine learning algorithm |
| CN108257214A (en) * | 2018-02-12 | 2018-07-06 | 成都信息工程大学 | Heart left ventricle flow field domain method for numerical simulation, computer, computer program |
| US20180242950A1 (en) * | 2017-02-28 | 2018-08-30 | Canon Medical Systems Corporation | Ultrasound diagnosis apparatus, image processing apparatus, and image processing method |
| CN109820594A (en) * | 2018-12-20 | 2019-05-31 | 天津市胸科医院 | A method of production heart part 3D printing model is guided using ultrasonic wave initial data |
| CN112424820A (en) * | 2018-07-13 | 2021-02-26 | 牙科监测公司 | Method for simulating a dental condition |
-
2020
- 2020-03-02 CN CN202010136356.3A patent/CN111180075B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4905706A (en) * | 1988-04-20 | 1990-03-06 | Nippon Colin Co., Ltd. | Method an apparatus for detection of heart disease |
| US20030093003A1 (en) * | 1999-09-29 | 2003-05-15 | Raymond Watrous | Multi-modal cardiac diagnostic decision support system and method |
| CN101916333A (en) * | 2010-08-12 | 2010-12-15 | 四川大学华西医院 | Transesophageal echocardiography visual simulation system and method |
| CN105474219A (en) * | 2013-08-28 | 2016-04-06 | 西门子公司 | Systems and methods for estimating physiological heart measurements from medical images and clinical data |
| US20180242950A1 (en) * | 2017-02-28 | 2018-08-30 | Canon Medical Systems Corporation | Ultrasound diagnosis apparatus, image processing apparatus, and image processing method |
| CN107348971A (en) * | 2017-08-17 | 2017-11-17 | 上海交通大学 | A kind of heart disease screening system based on heart sound detection and machine learning algorithm |
| CN108257214A (en) * | 2018-02-12 | 2018-07-06 | 成都信息工程大学 | Heart left ventricle flow field domain method for numerical simulation, computer, computer program |
| CN112424820A (en) * | 2018-07-13 | 2021-02-26 | 牙科监测公司 | Method for simulating a dental condition |
| CN109820594A (en) * | 2018-12-20 | 2019-05-31 | 天津市胸科医院 | A method of production heart part 3D printing model is guided using ultrasonic wave initial data |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117577301A (en) * | 2023-11-20 | 2024-02-20 | 四川大学华西医院 | Outside-hospital emergency system for automatic identification and intelligent auxiliary decision-making of cardiac arrest |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111180075B (en) | 2023-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Abbas et al. | Phonocardiography signal processing | |
| Thiyagaraja et al. | A novel heart-mobile interface for detection and classification of heart sounds | |
| Reed et al. | Heart sound analysis for symptom detection and computer-aided diagnosis | |
| JP2016513516A (en) | Systems and methods for individual hemodynamic modeling and monitoring | |
| JP2019058684A (en) | Biological information measurement device and method for operating biological information measurement device or biological information measurement system | |
| JPH06503483A (en) | Automatic digital image quantification system | |
| Mazumder et al. | Synthetic PPG signal generation to improve coronary artery disease classification: Study with physical model of cardiovascular system | |
| Akbari et al. | Digital Subtraction Phonocardiography (DSP) applied to the detection and characterization of heart murmurs | |
| Ahlström | Nonlinear phonocardiographic signal processing | |
| CN111180075A (en) | Dynamic model established based on heart murmur and computer simulation method | |
| Hossain et al. | Wavelet and spectral analysis of normal and abnormal heart sound for diagnosing cardiac disorders | |
| Andreou et al. | Mapping the cardiac acousteome: An overview of technologies, tools and methods | |
| Nizam et al. | Hilbert-envelope features for cardiac disease classification from noisy phonocardiograms | |
| Granados et al. | Acoustic heart. Interpretation of phonocardiograms by computer | |
| CN215349053U (en) | Congenital heart disease intelligent screening robot | |
| Sh-Hussain et al. | Application of multipoint auscultation for heart sound diagnostic system (MAHDS) | |
| Huang et al. | Augmented detection of septal defects using advanced optical coherence tomography network-processed phonocardiogram | |
| Rajeshwari et al. | Detection of phonocardiogram event patterns in mitral valve prolapse: An automated clinically relevant explainable diagnostic framework | |
| Casanella et al. | Cardiac Mechanical Signals | |
| Kumar | Automatic heart sound analysis for cardiovascular disease assessment | |
| Yuliang et al. | Quantized analysis for heart valve disease based on cardiac sound characteristic waveform method | |
| WO2024007152A1 (en) | Method for diagnosing pediatric cardiovascular diseases based on electrocardiographic and phonocardiographic signals | |
| CN117064446B (en) | Intravascular ultrasound-based vascular dynamic three-dimensional reconstruction system | |
| Visagie et al. | Autonomous detection of heart sound abnormalities using an auscultation jacket | |
| Salleh et al. | Heart Murmur Diagnostic System (HMDS) |
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 |