CN113576525A - Nondestructive intelligent thrombus detection device based on EMD and neural network - Google Patents
Nondestructive intelligent thrombus detection device based on EMD and neural network Download PDFInfo
- Publication number
- CN113576525A CN113576525A CN202110884748.2A CN202110884748A CN113576525A CN 113576525 A CN113576525 A CN 113576525A CN 202110884748 A CN202110884748 A CN 202110884748A CN 113576525 A CN113576525 A CN 113576525A
- Authority
- CN
- China
- Prior art keywords
- ultrasonic
- thrombus
- detection
- probe
- unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 208000007536 Thrombosis Diseases 0.000 title claims abstract description 80
- 238000001514 detection method Methods 0.000 title claims abstract description 51
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 20
- 239000000523 sample Substances 0.000 claims abstract description 45
- 210000004369 blood Anatomy 0.000 claims abstract description 30
- 239000008280 blood Substances 0.000 claims abstract description 30
- 238000012545 processing Methods 0.000 claims abstract description 29
- 210000003743 erythrocyte Anatomy 0.000 claims description 28
- 230000006870 function Effects 0.000 claims description 14
- 230000017531 blood circulation Effects 0.000 claims description 9
- 210000004204 blood vessel Anatomy 0.000 claims description 8
- 239000002245 particle Substances 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 4
- 210000000709 aorta Anatomy 0.000 claims description 3
- 239000007822 coupling agent Substances 0.000 claims description 2
- 238000012806 monitoring device Methods 0.000 claims 1
- 238000000034 method Methods 0.000 abstract description 12
- 230000008569 process Effects 0.000 abstract description 7
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000012544 monitoring process Methods 0.000 abstract description 3
- 238000000605 extraction Methods 0.000 abstract description 2
- 239000002023 wood Substances 0.000 abstract 1
- 239000000306 component Substances 0.000 description 7
- 208000032825 Ring chromosome 2 syndrome Diseases 0.000 description 6
- 230000006872 improvement Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- 238000012546 transfer Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 239000012503 blood component Substances 0.000 description 2
- 208000026106 cerebrovascular disease Diseases 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000002604 ultrasonography Methods 0.000 description 2
- 206010008088 Cerebral artery embolism Diseases 0.000 description 1
- 206010008132 Cerebral thrombosis Diseases 0.000 description 1
- 201000001429 Intracranial Thrombosis Diseases 0.000 description 1
- 208000032382 Ischaemic stroke Diseases 0.000 description 1
- 230000001154 acute effect Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000009098 adjuvant therapy Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 210000001627 cerebral artery Anatomy 0.000 description 1
- 230000002490 cerebral effect Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000001066 destructive effect Effects 0.000 description 1
- 238000013399 early diagnosis Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 239000008187 granular material Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000000338 in vitro Methods 0.000 description 1
- 238000001727 in vivo Methods 0.000 description 1
- 201000010849 intracranial embolism Diseases 0.000 description 1
- 208000028867 ischemia Diseases 0.000 description 1
- 238000010030 laminating Methods 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000009131 signaling function Effects 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/44—Constructional features of the ultrasonic, sonic or infrasonic diagnostic device
- A61B8/4427—Device being portable or laptop-like
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/08—Detecting organic movements or changes, e.g. tumours, cysts, swellings
- A61B8/0891—Detecting organic movements or changes, e.g. tumours, cysts, swellings for diagnosis of blood vessels
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/44—Constructional features of the ultrasonic, sonic or infrasonic diagnostic device
- A61B8/4444—Constructional features of the ultrasonic, sonic or infrasonic diagnostic device related to the probe
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/48—Diagnostic techniques
- A61B8/488—Diagnostic techniques involving Doppler signals
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Pathology (AREA)
- Radiology & Medical Imaging (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Vascular Medicine (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
Abstract
The invention discloses a nondestructive intelligent thrombus detection device based on EMD and a neural network. The wearing ring includes: the ultrasonic transmitting and receiving probe, the telescopic structure and the flexible wood wedge; the host includes: the ultrasonic monitoring system comprises an ultrasonic transmitting and receiving device, a data processing part, an equipment control unit and a display unit, wherein the data processing part comprises a Doppler signal processing unit, a thrombus judging unit and a recording unit, the judging unit intelligently judges the thrombus through a BP neural network, the recording unit counts the number scale of the thrombus, the display unit displays the detection result, and the equipment control unit controls the whole host. The technology of the invention is advanced and can realize nondestructive detection in the whole process without blood extraction; the flexible shell is adopted, so that the detection surface is more attached, and the acquired data is more accurate; the intelligent judgment is realized, the detection result is displayed visually, the operator is not required to have professional knowledge, and the intelligent detection device is more suitable for middle-aged and old users.
Description
Technical Field
The invention relates to the field of medical lesion detection and adjuvant therapy, in particular to a nondestructive intelligent thrombus detection device which can be used for detecting thrombus particles in superficial (in vivo) blood vessels.
Background
The thrombus can block the normal flow of blood flow, even can cause the blockage of blood vessels in severe cases, and the cerebral embolism is an acute cerebrovascular disease of corresponding cerebral tissue ischemia caused by the blockage of cerebral arteries by emboli entering blood circulation, is a main reason for generating ischemic stroke, has great harmfulness, so that the thrombus is accurately detected and identified, a reliable basis is provided for early diagnosis of the cerebrovascular disease, and the clinical significance is achieved.
The ultrasonic probe emits ultrasonic waves with certain intensity, when the ultrasonic waves meet moving blood, ultrasonic Doppler frequency shift is generated, the wavelength of the ultrasonic waves is larger than the diameter of red blood cells (the diameter of the red blood cells in blood components is the largest), the ultrasonic waves are scattered when meeting the red blood cells, and ultrasonic echo signals are only partial sound intensity scattered by the red blood cells; when thrombus with different diameters from red blood cells appears in blood, the thrombus forms an interface with blood flow, and the sound intensity of ultrasonic waves reflected by the interface between two media is in direct proportion to the difference of acoustic impedance between the two media. The greater the difference in density between the two media, the stronger the received echo signal. Because the reflected wave sound intensity between the blood and the thrombus is obviously greater than the scattering sound intensity, the characteristic values extracted by the two signals are different, and the thrombus in the blood can be detected through ultrasonic Doppler.
As an ultrasonic doppler technique for nondestructive examination of blood flow conditions, it has been widely used clinically. The technology can also be used for detecting thrombus information in blood flow, and the conventional transcranial ultrasonic Doppler instrument can be used for detecting cerebral thrombosis. However, in clinical application, thrombus signals are often distinguished by the experience of doctors, and a doppler system for automatically detecting thrombus is lacked. Therefore, how to accurately and automatically detect the thrombus by using the feature extraction method of the ultrasonic doppler blood flow signal becomes a popular research topic. The existing in-vitro thrombus detection instrument has the following defects:
firstly, the method comprises the following steps: a destructive detection method is mostly adopted, a small amount of blood of a patient needs to be extracted for detection, the pain of the patient is increased, and the operation of a professional is needed; secondly, the method comprises the following steps: the detection result can be judged only by an operator with professional knowledge, and is not beneficial to daily use of a patient; thirdly, the method comprises the following steps: most of existing detection instruments are professional detection equipment, and the existing detection instruments are not portable and inconvenient for daily use of patients. Fourthly: although the amplitude of the ultrasonic Doppler signal in the time domain is different due to the difference of the volumes of the thrombus and the red blood cells, the artificial interference signal caused by the sudden movement of the ultrasonic probe or the detected person in the detection process is very similar to the amplitude of the thrombus signal, so that the thrombus is judged to have a large error only by the amplitude of the time domain signal. Because the existing external thrombus detection instrument has many defects, it is very important to develop a nondestructive intelligent thrombus detection device which has simple structure, convenient operation and higher precision, can realize intelligent judgment and is more suitable for being placed on the surface of a human body and used for detecting superficial (internal) thrombus particles.
Disclosure of Invention
The invention aims to provide a nondestructive intelligent thrombus detection device based on EMD and a neural network, which has the advantages of high detection efficiency, accurate detection result, simple equipment, capability of monitoring thrombus patients in real time, cloud processing of monitoring data, real-time health analysis of network doctors and the like.
In order to solve the problems existing in the background technology and achieve the purposes, the invention is realized by the following technical scheme: a nondestructive intelligent thrombus detection device based on EMD and neural network comprises a wearing ring and a host, the wearable ring comprises an ultrasonic transmitting and receiving probe, a telescopic structure and a flexible wedge block, the host comprises an ultrasonic transmitting and receiving device, a data processing part, an equipment control unit and a display unit, the data processing part comprises a Doppler signal processing unit, a thrombus judging unit and a recording unit, the ultrasonic transmitting and receiving probe is connected with an ultrasonic transmitting and receiving device which is connected with a Doppler signal processing unit, the equipment control unit controls the whole host computer, the recording unit counts the number scale of thrombus, the display unit displays the detection result, the ultrasonic transmitting and receiving probe is embedded in the wearing ring, by transmitting and receiving ultrasonic waves into the blood vessel, doppler signals of different initial positions are acquired.
The ultrasonic transmitting and receiving probe is made of fully flexible materials, so that the probe can perfectly attach to the skin for operation (people can move normally), the ultrasonic probe transmits ultrasonic waves to detect an object and receives the ultrasonic waves reflected by the detected object.
As a further improvement of the present invention, since the ultrasonic echo signal is a nonlinear, non-stationary signal, the time-varying characteristics of the non-stationary signal cannot be well described by the conventional analysis method represented by fourier transform, and the Empirical Mode Decomposition (EMD) is an adaptive signal processing method based on time scale, which can well process the ultrasonic echo signal.
As a further improvement of the invention, the middle part of the left section and the right section of the wearable ring is provided with a telescopic structure, the host is provided with an adjusting button, and the wearable ring and the host are connected by a connecting wire. Adopt annular wearable device, the ultrasonic wave transmitting and receiving probe inlays wherein, and data are handled and are shown through wired connection to doppler signal processing unit, and it has the detection of deformable, more suitable position thrombus granule such as neck, head. The device is small and exquisite, portable, and is more suitable for the house to use.
As a further improvement of the invention, the whole detection process is lossless, blood does not need to be drawn, and a user only needs to wear the wearing ring to the neck and place the probe above the aorta.
As a further improvement of the invention, the detection result is intuitive and clear, and the operator does not need to have related professional knowledge.
As a further improvement of the invention, the ultrasonic probe embedded in the wearing ring adopts a 5MHz ultrasonic flat probe integrating receiving and transmitting, and the front part of the probe is provided with a flexible wedge block, so that the probe and the detection surface (the axial direction of the blood vessel) form an included angle of 16 degrees, and the oblique incidence of ultrasonic waves is realized.
The invention provides an EMD and neural network-based nondestructive intelligent thrombus detection device, which comprises the following specific steps:
the wearing ring is worn on the neck, the surface of the ultrasonic probe is coated with a coupling agent and is placed at the approximate position above the aorta, and then the inner side of the wearing ring is tightly attached to the surface of a human body through the tightness adjusting device. The ultrasonic wave transmitting and receiving device excites the ultrasonic probe to emit ultrasonic waves with certain intensity, and when the ultrasonic waves meet moving blood, ultrasonic Doppler frequency shift is generated. The wavelength of the ultrasonic wave is larger than the diameter (maximum diameter) of red blood cells in blood, the ultrasonic wave scatters when meeting the red blood cells, and the ultrasonic echo signal is only the partial sound intensity scattered back by the red blood cells; when thrombus with different diameters from red blood cells appears in blood, the thrombus forms an interface with blood flow, and the sound intensity of ultrasonic waves reflected by the interface between two media is in direct proportion to the difference of acoustic impedance between the two media. The greater the difference in density between the two media, the stronger the received echo signal. EMD processing is firstly carried out according to the detected ultrasonic signals of different media to obtain Intrinsic Mode Functions (IMF) of each order, frequency domain and time domain signals of IMF components of each order are input into a BP neural network as characteristic values to intelligently judge whether thrombus particles are contained in blood or not, the recording unit counts thrombus scale, and the display unit displays the detection result.
After the technical scheme is adopted, the invention has the following beneficial effects:
1. and (3) accurate detection: when blood contains thrombus, because the volume of thrombus is larger than that of main component (red blood cell) of blood, and thrombus and red blood cell have different acoustic impedances, the transmitting characteristics of ultrasonic wave by thrombus and red blood cell are greatly different, when ultrasonic wave meets thrombus, it will be reflected, and when it meets red blood cell, it will be scattered, and the sound intensity of reflected wave is obviously larger than that of scattered wave. Therefore, the difference that whether thrombus particles exist in blood is reflected in echo signals is obvious, intelligent judgment on the existence of the thrombus particles in the blood can be realized through EMD processing and a BP neural network, and the detection result is accurate.
2. The technology is advanced: nondestructive detection is carried out in the whole process, and blood does not need to be drawn; the flexible shell is adopted, so that the detection surface is more attached, and the data acquisition is more accurate;
3. the operation is convenient: the detection result is visually displayed by the display unit, so that an operator does not need to have professional knowledge, and the device is more suitable for middle-aged and elderly users;
small and portable: the scheme and the device are simple, small and portable, the size of the device is equivalent to that of a common household sphygmomanometer, the practicability is high, the detection efficiency is high, and the device is very suitable for being used at home.
Drawings
Embodiments of the present invention or prior art solutions will be more clearly described by reading the following drawings, which are simply presented for the sake of simplicity, and which are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without inventive step.
Fig. 1 is a schematic structural diagram of the apparatus provided in the present invention.
Fig. 2 is a schematic diagram of the overall functional modules of the apparatus provided in the present invention.
Fig. 3 is a schematic structural diagram of an ultrasonic transmitting and receiving probe in the device provided by the invention.
Fig. 4 is a schematic view of the working principle of the device provided by the invention.
FIG. 5 is a schematic view of the thrombus detection operation of the device of the present invention.
In the figure: the device comprises an ultrasonic probe-1, a wearing ring-2, a telescopic structure-3, a connecting line-4, a host computer-5, an adjusting knob-6, a display unit-7, a flexible wedge block-8, a blood vessel-9, red blood cells-10, thrombus-11, an ultrasonic transmitting and receiving device-12, a Doppler signal processing unit-13, a thrombus judging unit 14, a recording unit-15, a data processing part-16 and an equipment control unit-17.
Detailed description of the invention
In order to make the technical means, the creation characteristics, the achievement purposes and the effects of the invention more clear and clearer, the invention is further elaborated in the following by combining the attached drawings and the specific implementation method. It should be understood that the specific embodiments described herein are illustrative only and are not limiting upon the present invention.
Referring to fig. 1, the following technical solutions are adopted in the present embodiment: the utility model provides a harmless intelligent thrombus detection device based on EMD and neural network, includes ultrasonic probe 1, installs at wearing ring 2 fixed position, for conveniently wearing, is equipped with extending structure 3 on wearing ring 2, conveniently adjusts the elasticity and makes the inseparable laminating human tissue of wearing ring 2 ability. The ultrasonic probe 1 is connected with a host 5 through a connecting wire 4, and the host 5 is provided with an adjusting knob 6 and a display unit 7.
Referring to fig. 2, the ultrasonic probe 1 is a transceiver probe, and when in use, the probe is located right above the surface to be detected, the probe is connected to the host 5 through the connecting wire 4, the ultrasonic transmitter-receiver 12 excites the ultrasonic probe 1, the electric signal is converted into an ultrasonic signal through piezoelectric effect, the ultrasonic probe 1 sends out ultrasonic waves to detect human tissues, the detected echo signal is received by the ultrasonic probe 1 and converted into an electric signal through inverse piezoelectric effect, the ultrasonic transmitter-receiver 12 amplifies the signal and sends the signal to the doppler signal processing unit 13, namely, the ultrasonic transmitter-receiver 12 serves as both an ultrasonic excitation unit and an ultrasonic receiving unit. The switching between the transmission operation and the reception operation of the ultrasonic wave transmitter-receiver 12 is controlled by the control signal of the apparatus control unit 17, and the doppler signal processing unit 13 processes the ultrasonic doppler signal received by the ultrasonic wave transmitter-receiver 12, and when a thrombus is encountered due to the ultrasonic doppler signal, the power of the ultrasonic echo wave will be enhanced at the ultrasonic doppler frequency shift, after the doppler signal processing unit 13 performs EMD processing on the echo signal, the IMF characteristic value is sent to the thrombus judging unit 14 as a Doppler signal, then intelligent judgment is carried out on the IMF characteristic value through a BP neural network, every time the thrombus judging unit 14 detects the thrombus, the recording unit 15 records the IMF characteristic value and counts the thrombus value, the recording unit 15 sends the thrombus value detected within a specified time (for example, 30 minutes) to the display unit 7, and an operator can visually see the detection result. An adjusting knob 6 on the host 5 can adjust relevant parameters of the ultrasonic waves.
Referring to the data processing portion 16 of fig. 2, the doppler signal processing unit 13 performs EMD processing on the ultrasound echo signal to obtain a plurality of eigenmode functions (IMFs), each of which must satisfy two conditions: let us call the ultrasonic echo signal as the original signal s (t), and for each point of the whole signal s (t), the upper envelope e of the function maximum is fittedmax(t) lower envelope e fitted to the minimumminThe average value of (t) must be zero; for the whole signal function, the poleThe number of the value points is equal to the number of the zero crossing points or has a difference of 1 at most, all maximum value points and minimum value points of the original signal s (t) are firstly found, a maximum envelope curve and a minimum envelope curve of the signal are obtained by adopting 3 times of spline fitting, and an average envelope curve e of the signal s (t) is calculated according to the maximum envelope curve and the minimum envelope curveave(t) and average envelope eave(t)＝[emax(t)+emin(t)]2, subtracting the average envelope signal e from the original signal s (t)ave(t) obtaining a new signal s1(t) repeating the above process using the obtained new signal as an original signal until the condition of the eigenmode function is satisfied, defining the obtained function as an IMF1Then subtracting the eigenmode function IMF from the original signal s (t)1Processing the residual signal according to the steps to obtain IMF components of each order meeting the condition of the inherent mode function; the original ultrasound signal at this time can be expressed as:
performing correlation analysis on each order of IMF component and an original signal s (t), selecting the first four IMF components with high correlation with the original signal s (t) for analysis, and when analyzing the time domain of the IMF, adopting three characteristic parameters of zero crossing points, signal area and maximum amplitude as the time domain characteristic value of the IMF function; when the frequency domain of the IMF is analyzed, Fourier transform is firstly carried out on IMF functions of all components, and then three characteristic parameters, namely the maximum amplitude, the central frequency and the signal energy, are adopted as frequency domain characteristic values of the IMF, namely each IMF component has six characteristic parameters.
The judging unit 14 intelligently judges the thrombus through the trained BP neural network, and since the common ultrasonic echo signals in thrombus detection include a red blood cell 10 signal, a thrombus 11 signal and an artificial interference signal caused by sudden movement of an ultrasonic probe or a patient, the thrombus detection problem is converted into a classification problem of three signals, expected outputs of the three signals are encoded firstly, and are respectively a thrombus 11 signal (100), a red blood cell 10 signal (010) and an interference signal (001), and the three signals are used as output nodes of the BP neural network. The input layer nodes of the BP neural network are determined by the input feature vectors, so the specific structure of the BP neural network of the device is as follows: 24 input layer neurons, 20 hidden layer neurons, and 3 output layer neurons. The hyperbolic tangent sigmoid transfer function tansig serves as the transfer function of the hidden layer, while the sigmoid function logsig serves as the transfer function of the output layer.
Referring to fig. 3, which is a schematic structural diagram of an ultrasonic probe 1 in the device provided by the present invention, the ultrasonic probe 1 employs a 5MHz ultrasonic transceiver probe, the transceiver state is controlled by an ultrasonic transceiver 12, and a flexible wedge 8 is required to be installed at the front end of the ultrasonic probe 1, so that an included angle of 16 degrees is formed between the probe plane and the detection surface (the axial direction of the blood vessel), thereby realizing oblique incidence of ultrasonic waves.
Referring to fig. 4, which is a schematic view of the working principle of the device provided by the present invention, the ultrasonic transceiver 12 excites the ultrasonic probe 1 to emit ultrasonic waves with a certain intensity, the ultrasonic waves are obliquely incident into the blood vessel 9 through the wedge 8, and when the ultrasonic waves encounter moving blood, an ultrasonic doppler frequency shift is generated. Because the wavelength of the ultrasonic wave is greater than the diameter of the red blood cell 10 in the blood (the diameter of the red blood cell in the blood component is the largest), the ultrasonic wave scatters when meeting the red blood cell 10, and the ultrasonic echo signal received by the ultrasonic probe 1 is only the partial sound intensity scattered back by the red blood cell 10; when a thrombus 11 with a diameter different from that of the red blood cell 10 appears in blood, the thrombus 11 forms an interface with blood flow, the sound intensity of ultrasonic waves reflected by the interface between two media is in direct proportion to the acoustic impedance difference between the two media, and the larger the density difference between the two media is, the stronger the received echo signal is. Generally, the diameter of the thrombus 11 is about 0.15mm to 1.5mm, and the diameter of the red blood cell 10 with the largest diameter in the blood is about 0.6um, so the ultrasonic wave will scatter when meeting the red blood cell 10, and will reflect when meeting the thrombus 11, because the reflected wave sound intensity between the blood and the thrombus 11 is obviously greater than the scattered wave sound intensity, so the thrombus 11 in the blood can be detected by ultrasonic doppler, and if the thrombus enters the sampling system of the ultrasonic thrombus detection instrument at a certain moment, the power of the ultrasonic doppler signal will be increased, and the increase of the signal amplitude will continue until the thrombus leaves the sampling end moment of the instrument, the ultrasonic transceiver 12 receives the multiple ultrasonic doppler signal, and sends it to the data processing part 16, and makes intelligent judgment and counting for the thrombus through the BP neural network.
Please refer to fig. 5, which is a schematic view of the working state of the device for detecting human body according to the present invention, the wearing ring 2 is worn on the neck of the detected person and is fixed by the telescopic structure 3 of the wearing ring 2, so that the ultrasonic probe 1 is tightly attached to the neck skin of the detected person. The examination of the neck blood vessels can be completed within about 30 minutes, and the burden of the detected personnel is greatly reduced in time.
While there have been shown and described what are at present considered the fundamental principles of the invention, its essential features and advantages, it will be apparent to those skilled in the art that the invention is not limited to the details of the foregoing exemplary embodiments, but is capable of other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (4)
1. The utility model provides a harmless intelligent thrombus detection device based on EMD and neural network which characterized in that: the device is divided into two parts, a wearing ring (2) and a host (5), wherein the wearing ring (2) comprises: ultrasonic emission receiving probe (1), extending structure (3), flexible voussoir (8), host computer (5) include ultrasonic emission receiver (12), data processing part (16), equipment control unit (17) and display element (7), data processing part (16) include: the ultrasonic monitoring device comprises a Doppler signal processing unit (13), a thrombus judging unit (14) and a recording unit (15), wherein an ultrasonic transmitting and receiving probe (1) is connected with an ultrasonic transmitting and receiving device (12) through a connecting line (4), the ultrasonic transmitting and receiving device (12) is connected with the Doppler signal processing unit (13), the Doppler signal processing unit (13) carries out EMD processing on Doppler echo signals of different media to obtain a plurality of IMFs, then frequency domain and time domain analysis is carried out on the IMFs, frequency domain and time domain signals of IMF components of different orders are used as characteristic values to be input into the judging unit (14), the judging unit (14) carries out intelligent judgment on thrombus through a BP neural network, the recording unit (15) counts the number scale of the thrombus, the display unit (7) displays a detection result, and the equipment control unit (17) controls the whole host (5), the ultrasonic transmitting and receiving probe (1) is embedded in the wearable ring (2), and obtains Doppler signals at different initial positions by transmitting and receiving ultrasonic waves into the blood vessel (9).
2. The device according to claim 1, wherein the device comprises: the middle part of the left section and the right section of the wearable ring (2) is provided with a telescopic structure (3), the host (5) is provided with an adjusting knob (6), and the wearable ring (2) is connected with the host (5) through a connecting wire (4).
3. The device according to claim 1, wherein the ultrasonic thrombus detection method comprises:
(1) the wearing ring (2) is worn on the neck, the surface of the ultrasonic probe (1) is coated with a coupling agent, and the ultrasonic probe (1) is placed at the approximate position above the aorta;
(2) the tightness is adjusted through the telescopic structure (3) of the wearing ring (2), so that the inner side of the wearing ring (2) is tightly attached to the skin of a human body, the ultrasonic transmitter-receiver (12) excites the ultrasonic probe (1) to emit ultrasonic waves with certain intensity, and when the ultrasonic waves meet moving blood, ultrasonic Doppler frequency shift is generated;
(3) the wavelength of the ultrasonic wave is larger than the diameter of the red blood cells (10) in the blood, the ultrasonic wave is scattered when meeting the red blood cells (10), and the ultrasonic echo signal is only the partial sound intensity of the ultrasonic wave scattered back by the red blood cells (10); when thrombus (11) with different diameters from red blood cells appears in blood, the surface of the thrombus (11) forms an interface with blood flow, and the sound intensity of ultrasonic waves reflected by the interface between two media is in direct proportion to the difference of acoustic impedances between the two media;
(4) when the density difference of the two media is larger, the echo signal received by the ultrasonic probe (1) is stronger, the reflected wave sound intensity between the blood and the thrombus (11) is obviously larger than the scattering sound intensity between the blood and the red blood cells (10), and the thrombus can cause the power enhancement of the ultrasonic Doppler signal when passing through a detection instrument.
(5) EMD processing is firstly carried out according to the detected ultrasonic signals to obtain eigen mode functions (IMF) of each order, frequency domain and time domain signals of IMF components of each order are used as characteristic values to be input into a BP neural network to intelligently judge whether thrombus (11) particles are contained in blood or not, the recording unit (7) counts the scale of the thrombus (11), and the detection result is displayed by the display unit (7).
4. The nondestructive intelligent thrombus detection device based on EMD and neural network as claimed in claim 1, wherein the front end of the ultrasonic probe (1) is provided with a flexible wedge block (8), so that the ultrasonic probe (1) forms an included angle of 16 degrees with the detection surface, and the oblique incidence of ultrasonic waves is realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110884748.2A CN113576525A (en) | 2021-08-03 | 2021-08-03 | Nondestructive intelligent thrombus detection device based on EMD and neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110884748.2A CN113576525A (en) | 2021-08-03 | 2021-08-03 | Nondestructive intelligent thrombus detection device based on EMD and neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113576525A true CN113576525A (en) | 2021-11-02 |
Family
ID=78254482
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110884748.2A Pending CN113576525A (en) | 2021-08-03 | 2021-08-03 | Nondestructive intelligent thrombus detection device based on EMD and neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113576525A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102855623A (en) * | 2012-07-19 | 2013-01-02 | 哈尔滨工业大学 | Method for measuring myocardium ultrasonic angiography image physiological parameters based on empirical mode decomposition (EMD) |
| CN109124688A (en) * | 2018-10-09 | 2019-01-04 | 南昌航空大学 | A kind of wearable ultrasonic thrombus detection device |
| CN109431767A (en) * | 2018-10-17 | 2019-03-08 | 东北大学 | A kind of intelligent control method of rehabilitation medical air cushion clothes |
-
2021
- 2021-08-03 CN CN202110884748.2A patent/CN113576525A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102855623A (en) * | 2012-07-19 | 2013-01-02 | 哈尔滨工业大学 | Method for measuring myocardium ultrasonic angiography image physiological parameters based on empirical mode decomposition (EMD) |
| CN109124688A (en) * | 2018-10-09 | 2019-01-04 | 南昌航空大学 | A kind of wearable ultrasonic thrombus detection device |
| CN109431767A (en) * | 2018-10-17 | 2019-03-08 | 东北大学 | A kind of intelligent control method of rehabilitation medical air cushion clothes |
Non-Patent Citations (2)
| Title |
|---|
| FANG J，等: "Discrimination between newly formed and aged thrombi using empirical mode decomposition of ultrasound B-scan image", BIOMED RESEARCH INTERNATIONAL, 28 January 2015 (2015-01-28), pages 1 - 9 * |
| 陈曦, 等: "血栓多普勒信号的多参数提取及分类", 声学技术, 30 March 2004 (2004-03-30), pages 20 - 24 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CA3005790C (en) | Systems and methods for automated fluid response measurement | |
| US5766208A (en) | Body monitoring and imaging apparatus and method | |
| Semmlow et al. | Acoustic detection of coronary artery disease | |
| US20070239003A1 (en) | Apparatus and methods for acoustic diagnosis | |
| US11406348B2 (en) | Method of detecting dicrotic notch | |
| WO2014053080A1 (en) | Integrated diagnosis/treatment device for mastopathy | |
| CN101987022B (en) | Ultrasonic real-time monitoring and wireless alarming system for bladder capacity | |
| CN109124688A (en) | A kind of wearable ultrasonic thrombus detection device | |
| CN109640828B (en) | Ultrasonic blood flow monitoring | |
| CN107411774A (en) | A kind of wearable ultrasonic thrombus detection means | |
| Shi et al. | Neural network based real-time heart sound monitor using a wireless wearable wrist sensor | |
| Shomaji et al. | Early detection of cardiovascular diseases using wearable ultrasound device | |
| CN113576525A (en) | Nondestructive intelligent thrombus detection device based on EMD and neural network | |
| US20230011862A1 (en) | Systems and methods for automated fluid response measurement | |
| JP2021108799A (en) | Ultrasonic urine amount measuring device, learning model generation method, and learning model | |
| CN111343923A (en) | Non-invasive heart valve screening device and method | |
| CN216702565U (en) | Wearable visual ultrasonic noninvasive monitoring instrument | |
| TWI773472B (en) | Array measuring method and interpretation device for ultrasonic detection of middle ear effusion | |
| CN202015194U (en) | Concave-array ultrasonic probe | |
| Xu | Local measurement of the pulse wave velocity using Doppler ultrasound | |
| RU211777U1 (en) | ULTRASONIC DEVICE FOR DIAGNOSTICS OF SOLID INCLUSIONS | |
| US20230116718A1 (en) | Enhanced Resolution Stethoscope | |
| WO2022155015A1 (en) | Non-invasive non-compressive blood pressure monitoring device | |
| WO2020029255A1 (en) | Method and device for combined measurement of changes in mechanical vibration parameters at multiple points on human body over time | |
| CN112869765A (en) | Fetal heart rate calculation method and wearable heart-lung sound wireless monitoring system |
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 |