CN108354629A - Supersonic wave imaging method - Google Patents
Supersonic wave imaging method Download PDFInfo
- Publication number
- CN108354629A CN108354629A CN201810297712.2A CN201810297712A CN108354629A CN 108354629 A CN108354629 A CN 108354629A CN 201810297712 A CN201810297712 A CN 201810297712A CN 108354629 A CN108354629 A CN 108354629A
- Authority
- CN
- China
- Prior art keywords
- blood flow
- signal
- neural network
- imaging method
- vessel position
- 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.)
- Withdrawn
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/06—Measuring blood flow
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/08—Clinical applications
- A61B8/0891—Clinical applications 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
- A61B8/48—Diagnostic techniques
- A61B8/488—Diagnostic techniques involving Doppler signals
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/5207—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of raw data to produce diagnostic data, e.g. for generating an image
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/5215—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data
- A61B8/5238—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data for combining image data of patient, e.g. merging several images from different acquisition modes into one image
- A61B8/5246—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data for combining image data of patient, e.g. merging several images from different acquisition modes into one image combining images from the same or different imaging techniques, e.g. color Doppler and B-mode
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Pathology (AREA)
- Radiology & Medical Imaging (AREA)
- Biomedical Technology (AREA)
- Veterinary Medicine (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Hematology (AREA)
- Vascular Medicine (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
Abstract
The present invention discloses a kind of Supersonic wave imaging method, comprises the steps of：Emit a plurality of ultrasonic signals with pulse-recurrence time interval；Receive a plurality of reflection signals of ultrasonic signal；With neural network blood flow signal and clutter signal are separated by signal is reflected；Blood flow parameter is calculated according to blood flow signal；Judge vessel position according to blood flow parameter；And according to blood flow parameter and the corresponding image signal of vessel position adjustment reflection signal, ultrasound video is generated according to this.
Description
Technical field
The present invention is about a kind of Supersonic wave imaging method, espespecially a kind of Supersonic wave imaging method suitable for blood flow detecting.
Background technology
Since ultrasound scanning has the characteristic for not destroying material structure and human body cell, thus it is commonly applied to
Material Field and clinical medicine detection.In general, color Doppler (color Doppler) ultrasonic and power doppler
(power Doppler) ultrasonic is commonly applied to the detecting of the blood flow state in clinical diagnosis.However, blood flow detecting is easy by people
The shadow of body tissue disturbance is to and reducing the accuracy of detecting.Currently, the color Doppler ultrasonic of prior art and energy are more
General Le ultrasonic is divided with wall filter (wall filter) or adaptive wall filter (adaptive wall filter)
From clutter signal (clutter signal) caused by blood flow signal and tissue disturbance.However, the change for small blood flow
For change, the frequency band distribution of blood flow signal can overlap together with the frequency band distribution of clutter signal so that wall filter is not easy
Blood flow signal and clutter signal are efficiently separated, and then lead to not detect small blood flow.In addition, the previous skill in part
Art carries out signal analysis using the mode of singular value decomposition (singular value decomposition, SVD), by blood flow
Signal is efficiently separated with clutter signal.However, SVD needs complicated matrix operation so that operand is excessively huge and causes
The degree of difficulty that hardware is realized.
Invention content
It is above-mentioned to solve one of the objects of the present invention is to provide a kind of Supersonic wave imaging method suitable for blood flow detecting
Problem.
According to an embodiment, Supersonic wave imaging method of the present invention comprises the steps of：Emitted with pulse-recurrence time interval
A plurality of ultrasonic signals；Receive a plurality of reflection signals of ultrasonic signal；With neural network blood is separated by signal is reflected
Flow signal and clutter signal；Blood flow parameter is calculated according to blood flow signal；Judge vessel position according to blood flow parameter；And according to
Blood flow parameter and the corresponding image signal of vessel position adjustment reflection signal, generate ultrasound video according to this.
Preferably, the corresponding image of a plurality of reflection signals is adjusted according to the blood flow parameter and the vessel position to interrogate
Number, it is to generate black and white ultrasound videos according to a plurality of reflection signals, according to this according to this in the step of generation ultrasound video
Blood flow parameter and the vessel position adjust the corresponding color parameter of blood flow signal, generate colored ultrasound video, and should
Colored ultrasound video and the black and white ultrasound video are combined into the ultrasound video.
Preferably, which is blood flow velocity or the signal strength of the blood flow signal.
Preferably, which is calculated according to the blood flow signal with the neural network.
Preferably, it is that the vessel position is judged according to the blood flow parameter with the neural network.
Preferably, which is convolutional Neural network, which presets convolution kernel size, blood flow ginseng
Number is blood flow velocity, which additionally comprises the following steps：
According to the blood flow velocity adjust pulse-recurrence time interval with the convolution kernel size at the convolutional Neural network
At least one.
Preferably, it also comprises the steps of：The signal that next ultrasound video is adjusted according to the vessel position handles model
It encloses.
According to another embodiment, Supersonic wave imaging method of the invention comprises the steps of：With pulse-recurrence time interval
Emit a plurality of ultrasonic signals；Receive a plurality of reflection signals of ultrasonic signal；Reflection signal is separated into blood flow signal
And clutter signal；Blood flow velocity is calculated according to blood flow signal；Judge vessel position according to blood flow velocity；According to blood flow velocity tune
Whole pulse repetition interval, and/or the corresponding signal process range of reflection signal is adjusted according to vessel position；And according to blood
Parameter and the corresponding image signal of vessel position adjustment reflection signal are flowed, generates ultrasound video according to this.
Preferably, the corresponding image signal of such reflection signal is adjusted according to the blood flow velocity and the vessel position, according to
In the step of generating ultrasound video, to be to generate black and white ultrasound video according to a plurality of reflection signals, according to the blood flow
Flow velocity and the vessel position adjust the corresponding color parameter of blood flow signal, generate colored ultrasound video, and by the colour
Ultrasound video and the black and white ultrasound video are combined into the ultrasound video.
Preferably, which is separated by the blood flow signal with convolutional Neural network and the clutter is interrogated
Number.
Preferably, which is calculated according to the blood flow signal with the convolutional Neural network.
Preferably, which is judged according to the blood flow velocity with the convolutional Neural network.
Preferably, which presets convolution kernel size, and the blood flow velocity is adjusting the pulse-recurrence time
At least one of the convolution kernel size at interval and the convolutional Neural network.
In conclusion the present invention replaces the wall filter or adaptive wall filter of prior art with neural network, to divide
Thereby the degree of difficulty of hardware realization can be effectively reduced from clutter signal caused by blood flow signal and tissue disturbance.In addition,
The present invention can adjust pulse-recurrence time interval according to blood flow velocity, and/or corresponding according to vessel position adjustment reflection signal
Signal process range thereby can carry out optimized adjustment, so that blood flow detecting is more efficiently and more acurrate to systematic parameter.
It can be obtained further by detailed description of the invention below and institute's accompanying drawings about the advantages and spirit of the present invention
Solution.
Description of the drawings
Fig. 1 is the flow chart according to the Supersonic wave imaging method of one embodiment of the invention.
Fig. 2 is the signal that the reflection signal of ultrasonic signal is separated into blood flow signal and clutter signal by neural network
Figure.
Fig. 3 is the flow chart according to the Supersonic wave imaging method of another embodiment of the present invention.
Fig. 4 is the flow chart according to the Supersonic wave imaging method of another embodiment of the present invention..
Specific implementation mode
To make to have further understanding to the purpose of the present invention, construction, feature and its function, hereby coordinate embodiment specifically
It is bright as follows.
It please refers to Fig.1 and Fig. 2, Fig. 1 is according to the flow chart of the Supersonic wave imaging method of one embodiment of the invention, Fig. 2
The reflection signal of ultrasonic signal is separated into the schematic diagram of blood flow signal and clutter signal for neural network.It is shown in FIG. 1
Supersonic wave imaging method is suitable for color Doppler (color Doppler) ultrasonic and power doppler (power
Doppler) ultrasonic, to carry out blood flow detecting and generate ultrasound video according to this.
When carrying out ultrasound scanning to a subject matter (not shown), the operable ultrasound scanner head (not shown) of operating personnel
Emit a plurality of ultrasonic signals (in Fig. 1 with a pulse-recurrence time interval (pulse repetition interval, PRI)
Step S10), and receive a plurality of reflection signals (the step S12 in Fig. 1) for being reflected from subject matter of ultrasonic signal.Then,
As shown in Fig. 2, the present invention is to be separated into blood flow signal and the clutter signal (step in Fig. 1 by signal is reflected with a neural network
Rapid S14).In this embodiment, above-mentioned neural network can be convolutional Neural network (Convolution Neural
Network, CNN) or other similar neural network.
In this embodiment, neural network is trained in advance, the reflection signal of ultrasonic signal to be separated into
Blood flow signal and clutter signal.The present invention can prepare plural groups training sample in advance, wherein each group of training sample wraps respectively
Reflection signal containing ultrasonic signal shown in Fig. 2, and blood flow signal that thus the reflection signal of ultrasonic signal is isolated
With clutter signal.
Then, then by training sample input neural network, with to neural network into the reflection signal for being about to ultrasonic signal
It is separated into the training of blood flow signal and clutter signal.It should be noted that the detailed training process of neural network is prior art
People known to, details are not described herein.In addition, the neural network for that can support high complex calculation, the present invention can increase adjacent
The feature between feature and different images between scan line is analyzed and is captured, and to reach strengthens blood flow signal and clutter signal
Identification.
After obtaining blood flow signal, the present invention can calculate blood flow parameter (the step S16 in Fig. 1) according to blood flow signal,
Wherein blood flow parameter can be the signal strength of blood flow velocity or blood flow signal.If the Supersonic wave imaging method of the present invention is applied to coloured silk
Color doppler ultrasound, then above-mentioned blood flow parameter can be blood flow velocity.It should be noted that calculating blood flow stream according to blood flow signal
The method of speed is known to the people of prior art, and details can refer to " C.Kasai, K.Namekawa, A.Koyano, and
R.Omoto,Real-Time Two Dimensional Blood Flow Imaging Using an Autocorrelation
Technique, IEEE Trans.Sonics Ultrasonics, vol.SU-32, pp.458-464,1985. ", herein no longer
It repeats.In addition, if the Supersonic wave imaging method of the present invention is applied to power doppler ultrasonic, above-mentioned blood flow parameter can be
The signal strength of blood flow signal.It should be noted that the method for calculating the signal strength of blood flow signal according to blood flow signal is also to practise
Know known to the people of skill, also repeats no more herein.
After obtaining blood flow parameter, the present invention can judge vessel position (the step S18 in Fig. 1) according to blood flow parameter.
It should be noted that judging the method for vessel position for known to the people of prior art, details can refer to according to blood flow parameter
“Efficient Implementation of Ultrasound Color Doppler Algorithms on Texas
Instruments'C64xTMPlatforms ", details are not described herein.
Then, the present invention can adjust the corresponding image signal of reflection signal according to blood flow parameter and vessel position,
Ultrasound video (the step S20 in Fig. 1) is generated according to this.In this embodiment, the present invention can generate black and white according to reflection signal
Ultrasound video, wherein black and white ultrasound video are generated with B-mode (B mode).Meanwhile the present invention can be according to blood flow parameter
And the corresponding color parameter of vessel position adjustment blood flow signal, and generate colored ultrasound video, wherein vessel position be with
The color parameter of corresponding blood flow parameter is shown in colored ultrasound video.Then, then by colored ultrasound video and black and white
Ultrasound video is combined into above-mentioned ultrasound video.
Since the present invention is to replace the wall filter or adaptive wall filter of prior art with neural network, to detach blood
Flowing clutter signal caused by signal and tissue disturbance thereby can effectively reduce the degree of difficulty of hardware realization.
Referring to Fig. 3, Fig. 3 is the flow chart according to the Supersonic wave imaging method of another embodiment of the present invention.It is shown in Fig. 3
It is in place of Supersonic wave imaging method and the main difference of Supersonic wave imaging method shown in FIG. 1, ultrasonic imaging shown in Fig. 3
The step S16' of method is to calculate blood flow parameter, and Supersonic wave imaging method shown in Fig. 3 according to blood flow signal with neural network
Step S18' be that vessel position is judged according to blood flow parameter with neural network.In other words, Supersonic wave imaging method shown in Fig. 3
It is that blood flow signal and clutter signal are separated by signal is reflected with neural network, blood is calculated according to blood flow signal with neural network
Parameter is flowed, and vessel position is judged according to blood flow parameter with neural network.In this embodiment, the present invention can prepare plural number in advance
Group training sample, wherein each group of training sample separately includes and corresponding to be in 256 rank colors mapping (color mapping)
The image pattern of the blood flow signal and clutter signal of existing doppler shifted frequency (Doppler shift frequency).It connects
It, then training sample is inputted into neural network, to be trained to neural network.It should be noted that the detailed instruction of neural network
Practice known to the people that process system is prior art, details are not described herein.
When above-mentioned neural network be convolutional Neural network, and blood flow parameter be blood flow velocity when, ultrasonic of the invention at
Image space method can further adjust the convolution kernel size at pulse-recurrence time interval and convolutional Neural network according to blood flow velocity
At least one of (kernel size), so that blood flow detecting is more efficiently and more acurrate.For example, work as blood flow velocity
When faster, pulse-recurrence time interval can be made to reduce therewith；When blood flow velocity is slower, pulse-recurrence time interval can be made therewith
Increase.For example, when blood flow velocity is faster, convolution kernel size can be made to reduce therewith；When blood flow velocity is slower, volume can be made
Product core size increases therewith.It should be noted that convolution kernel size is default with identification in being trained by convolutional Neural network, by
It is known to the people of prior art in the action principle of the convolution kernel size at convolutional Neural network, details are not described herein.
In addition, the Supersonic wave imaging method of the present invention also further can adjust next ultrasound video according to vessel position
Signal process range.Furthermore, it is understood that when the vessel position in i-th ultrasound video is known, the present invention, that is, adjustable
The signal process range of whole i+1 ultrasound video (also that is, next ultrasound video of i-th ultrasound video) is to contain
Lid i-th opens the range of the vessel position in ultrasound video, without to the non-vascular position in i+1 ultrasound video
Signal is handled.Thereby, you can effectively reduce operand.
Referring to Fig. 4, Fig. 4 is the flow chart according to the Supersonic wave imaging method of another embodiment of the present invention.It is shown in Fig. 4
Supersonic wave imaging method is suitable for color Doppler ultrasonic, to carry out blood flow detecting and generate ultrasound video according to this.
When carrying out ultrasound scanning to a subject matter (not shown), the operable ultrasound scanner head (not shown) of operating personnel
Emit a plurality of ultrasonic signals (in Fig. 4 with pulse-recurrence time interval (pulse repetition interval, PRI)
Step S30), and receive a plurality of reflection signals (the step S32 in Fig. 4) that ultrasonic signal is reflected from subject matter.Then, will
Reflection signal is separated into blood flow signal and clutter signal (the step S34 in Fig. 4).In this embodiment, the present invention can god
Through network, wall filter or adaptive wall filter blood flow signal and clutter signal are separated by signal is reflected.
After obtaining blood flow signal, the present invention can calculate blood flow velocity (the step S36 in Fig. 4) according to blood flow signal.
It should be noted that being known to the people of prior art according to the method that blood flow signal calculates blood flow velocity, details can refer to
“C.Kasai,K.Namekawa,A.Koyano,and R.Omoto,Real-Time Two Dimensional Blood Flow
Imaging Using an Autocorrelation Technique,IEEE Trans.Sonics Ultrasonics,
Vol.SU-32, pp.458-464,1985. ", details are not described herein.
After obtaining blood flow velocity, the present invention can judge vessel position (the step S38 in Fig. 4) according to blood flow velocity.
It should be noted that judging the method for vessel position for known to the people of prior art, details can refer to according to blood flow velocity
“Efficient Implementation of Ultrasound Color Doppler Algorithms on Texas
Instruments'C64xTMPlatforms ", details are not described herein.
Then, the present invention can adjust pulse-recurrence time interval according to blood flow velocity, and/or be adjusted according to vessel position
The corresponding signal process range (the step S40 in Fig. 4) of signal is reflected, so that blood flow detecting is more efficiently and more acurrate.It needs
Bright, pulse-recurrence time interval is with the adjustment mode of signal process range as described above, details are not described herein.
Then, the present invention can reflect the corresponding image signal of signal according to blood flow velocity and vessel position adjustment, according to
To generate ultrasound video (the step S42 in Fig. 4).In this embodiment, it is super that the present invention can generate black and white according to reflection signal
Sound wave image, wherein black and white ultrasound video are generated with B-mode.Meanwhile the present invention can be according to blood flow velocity and blood vessel position
The corresponding color parameter of adjustment blood flow signal is set, and generates colored ultrasound video, wherein vessel position is to correspond to blood flow stream
The color parameter of speed is shown in colored ultrasound video.Then, then by colored ultrasound video and black and white ultrasound video
It is combined into above-mentioned ultrasound video.
In another embodiment, the present invention can be separated into blood flow signal and clutter with convolutional Neural network by signal is reflected
Signal is calculated blood flow velocity according to blood flow signal with convolutional Neural network, and/or is sentenced according to blood flow velocity with convolutional Neural network
Disconnected vessel position.At this point, the predeterminable convolution kernel size in convolutional Neural network.It should be noted that convolution kernel size is convolutional Neural
Network in be trained with identification preset, due to convolutional Neural network convolution kernel size action principle for prior art it
Known to people, details are not described herein.Therefore, after obtaining blood flow velocity, between blood flow velocity can be used to adjust pulse-recurrence time
Every at least one of the convolution kernel size with convolutional Neural network, so that blood flow detecting is more efficiently and more acurrate.Citing
For, when blood flow velocity is faster, pulse-recurrence time interval can be made to reduce therewith；When blood flow velocity is slower, pulse can be made
Repetition interval increases therewith.For example, when blood flow velocity is faster, convolution kernel size can be made to reduce therewith；Work as blood flow
When flow velocity is slower, convolution kernel size can be made to increase therewith.
In conclusion the present invention is to replace the wall filter or adaptive wall filter of prior art with neural network, come
Detaching clutter signal caused by blood flow signal and tissue disturbance thereby can effectively reduce the degree of difficulty of hardware realization.This
Outside, the present invention can be adjusted according to blood flow velocity pulse-recurrence time interval with the convolution kernel size at convolutional Neural network at least its
One of, and/or systematic parameter can thereby be carried out according to the signal process range of vessel position adjustment reflection signal correspondence
Optimized adjustment, so that blood flow detecting is more efficiently and more acurrate.
The present invention is described by above-mentioned related embodiment, however above-described embodiment is only the example for implementing the present invention.
It must be noted that the embodiment disclosed is not limiting as the scope of the present invention.On the contrary, do not depart from the present invention spirit and
It is changed and retouched made by range, belongs to the scope of patent protection of the present invention.
Claims (13)
1. a kind of Supersonic wave imaging method, which is characterized in that comprise the steps of：
Emit a plurality of ultrasonic signals with pulse-recurrence time interval；
Receive a plurality of reflection signals of a plurality of ultrasonic signals；
A plurality of reflection signals are separated into blood flow signal and clutter signal with neural network；
Blood flow parameter is calculated according to the blood flow signal；
Judge vessel position according to the blood flow parameter；And
The corresponding image signal of a plurality of reflection signals is adjusted according to the blood flow parameter and the vessel position, is generated according to this super
Sound wave image.
2. Supersonic wave imaging method as described in claim 1, which is characterized in that according to the blood flow parameter and the vessel position
It is a plurality of according to this in the step of adjusting the corresponding image signal of a plurality of reflection signals, generating ultrasound video according to this
It reflects signal and generates black and white ultrasound video, which is adjusted according to the blood flow parameter and the vessel position
Color parameter generates colored ultrasound video, and the colour ultrasound video and the black and white ultrasound video is combined into this and is surpassed
Sound wave image.
3. Supersonic wave imaging method as described in claim 1, which is characterized in that the blood flow parameter is blood flow velocity or the blood flow
The signal strength of signal.
4. Supersonic wave imaging method as described in claim 1, which is characterized in that by the neural network according to the blood flow signal in terms of
Calculate the blood flow parameter.
5. Supersonic wave imaging method as described in claim 1, which is characterized in that be with the neural network according to the blood flow parameter
Judge the vessel position.
6. Supersonic wave imaging method as described in claim 1, which is characterized in that the neural network is convolutional Neural network, should
Convolution kernel size is preset at convolutional Neural network, which is blood flow velocity, which additionally comprises following step
Suddenly：
Pulse-recurrence time interval is adjusted according to the blood flow velocity with the convolution kernel size at the convolutional Neural network at least
One of them.
7. Supersonic wave imaging method as described in claim 1, which is characterized in that also comprise the steps of：
The signal process range of next ultrasound video is adjusted according to the vessel position.
8. a kind of Supersonic wave imaging method, which is characterized in that comprise the steps of：
Emit a plurality of ultrasonic signals with pulse-recurrence time interval；
Receive a plurality of reflection signals of a plurality of ultrasonic signals；
A plurality of reflection signals are separated into blood flow signal and clutter signal；
Blood flow velocity is calculated according to the blood flow signal；
Judge vessel position according to the blood flow velocity；
The pulse-recurrence time interval is adjusted according to the blood flow velocity, and/or such reflection signal is adjusted according to the vessel position
Corresponding signal process range；And
A plurality of reflection signals are adjusted according to the blood flow velocity and the vessel position and correspond to volume image signal, are generated according to this super
Sound wave image.
9. Supersonic wave imaging method as claimed in claim 8, which is characterized in that according to the blood flow velocity and the vessel position
It is a plurality of according to this in the step of adjusting one of such reflection signal correspondence image signal, generating a ultrasound video according to this
It reflects signal and generates black and white ultrasound video, which is adjusted according to the blood flow velocity and the vessel position
Color parameter generates colored ultrasound video, and the colour ultrasound video and the black and white ultrasound video is combined into this and is surpassed
Sound wave image.
10. Supersonic wave imaging method as claimed in claim 8, which is characterized in that with convolutional Neural network that this is a plurality of anti-
It penetrates signal and is separated into the blood flow signal and the clutter signal.
11. Supersonic wave imaging method as claimed in claim 10, which is characterized in that with the convolutional Neural network according to the blood flow
Signal calculates the blood flow velocity.
12. Supersonic wave imaging method as claimed in claim 10, which is characterized in that with the convolutional Neural network according to the blood flow
Flow velocity judges the vessel position.
13. Supersonic wave imaging method as claimed in claim 10, which is characterized in that it is big that convolution kernel is preset at the convolutional Neural network
It is small, the blood flow velocity to adjust pulse-recurrence time interval with the convolution kernel size at the convolutional Neural network at least its
One of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810297712.2A CN108354629A (en) | 2018-03-30 | 2018-03-30 | Supersonic wave imaging method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810297712.2A CN108354629A (en) | 2018-03-30 | 2018-03-30 | Supersonic wave imaging method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108354629A true CN108354629A (en) | 2018-08-03 |
Family
ID=63001599
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810297712.2A Withdrawn CN108354629A (en) | 2018-03-30 | 2018-03-30 | Supersonic wave imaging method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108354629A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI678185B (en) * | 2018-10-04 | 2019-12-01 | 宏碁股份有限公司 | Ultrasonic-based pulse-taking device and pulse-taking method thereof |
| WO2020051899A1 (en) * | 2018-09-14 | 2020-03-19 | 深圳迈瑞生物医疗电子股份有限公司 | Blood vessel position display method and ultrasonic imaging system |
| CN111067570A (en) * | 2018-10-18 | 2020-04-28 | 宏碁股份有限公司 | Ultrasound-based Pulse Diagnosis Instrument and Pulse Diagnosis Method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1984607A (en) * | 2004-10-20 | 2007-06-20 | 株式会社东芝 | Ultrasonic doppler diagnosis device |
| CN102100567A (en) * | 2009-12-21 | 2011-06-22 | 株式会社东芝 | Color doppler ultrasonic diagnosis apparatus |
| CN102525563A (en) * | 2010-11-25 | 2012-07-04 | 株式会社东芝 | Ultrasound diagnosis apparatus, image generating method, and image processing apparatus |
| CN105962904A (en) * | 2016-04-21 | 2016-09-28 | 西安工程大学 | Human tissue focus detection method based on infrared thermal imaging technology |
| US20170135675A1 (en) * | 2015-11-12 | 2017-05-18 | Vanderbilt University | Adaptive clutter demodulation for ultrasound imaging |
-
2018
- 2018-03-30 CN CN201810297712.2A patent/CN108354629A/en not_active Withdrawn
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1984607A (en) * | 2004-10-20 | 2007-06-20 | 株式会社东芝 | Ultrasonic doppler diagnosis device |
| CN102100567A (en) * | 2009-12-21 | 2011-06-22 | 株式会社东芝 | Color doppler ultrasonic diagnosis apparatus |
| US20110152689A1 (en) * | 2009-12-21 | 2011-06-23 | Takeshi Sato | Color doppler ultrasonic diagnosis apparatus |
| CN102525563A (en) * | 2010-11-25 | 2012-07-04 | 株式会社东芝 | Ultrasound diagnosis apparatus, image generating method, and image processing apparatus |
| US20170135675A1 (en) * | 2015-11-12 | 2017-05-18 | Vanderbilt University | Adaptive clutter demodulation for ultrasound imaging |
| CN105962904A (en) * | 2016-04-21 | 2016-09-28 | 西安工程大学 | Human tissue focus detection method based on infrared thermal imaging technology |
Non-Patent Citations (3)
| Title |
|---|
| SUNGJOON YOON等: "Performance Evaluation of Neural Network Based Ultrasonic Flaw Detection", 《INTERNALTIONAL ULTRASONICS SYMPOSIUM》 * |
| VICEN R等: "Non-linear filtering of ultrasonic signals using neural networks", 《ULTRASONICS》 * |
| 董正宏等: "一种结构噪声抑制的非线性滤波器算法及模型", 《JOURNAL OF SYSTEM SIMULATION》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020051899A1 (en) * | 2018-09-14 | 2020-03-19 | 深圳迈瑞生物医疗电子股份有限公司 | Blood vessel position display method and ultrasonic imaging system |
| TWI678185B (en) * | 2018-10-04 | 2019-12-01 | 宏碁股份有限公司 | Ultrasonic-based pulse-taking device and pulse-taking method thereof |
| CN111067570A (en) * | 2018-10-18 | 2020-04-28 | 宏碁股份有限公司 | Ultrasound-based Pulse Diagnosis Instrument and Pulse Diagnosis Method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP0226044B1 (en) | Display of a stream line of an inhomogeneous flowing medium | |
| JP5048175B2 (en) | An ultrasound system that executes computer instructions in parallel | |
| US9895138B2 (en) | Ultrasonic diagnostic apparatus | |
| US20190365354A1 (en) | Ultrasonic blood flow parameter displaying method, and ultrasonic imaging system therefor | |
| US20210369241A1 (en) | Imaging system and method with live examination completeness monitor | |
| JP2001128976A (en) | Method and device for prf control, and ultrasonographic apparatus | |
| US20100125201A1 (en) | Ultrasound imaging apparatus | |
| CN108354629A (en) | Supersonic wave imaging method | |
| CN110074818A (en) | A kind of supersonic blood calculates and display methods and system | |
| CN111714157A (en) | Doppler ultrasonic blood flow automatic identification method and device | |
| TWI682169B (en) | Ultrasound imaging method | |
| US5072734A (en) | Pulse doppler mti system | |
| US6485424B2 (en) | Image forming method and apparatus, and ultrasonic imaging apparatus | |
| JPH0595947A (en) | Ultrasonic diagnostic apparatus | |
| US20070073152A1 (en) | Systems and methods for acquiring images simultaneously | |
| JP2719707B2 (en) | Image display method of color Doppler MTI device | |
| US20200178935A1 (en) | Method and system for simultaneously presenting doppler signals of a multi-gated doppler signal corresponding with different anatomical structures | |
| US20180367126A1 (en) | Pulse Cancellation Compensation Method for Contrast Agent Imaging | |
| JP2009112491A (en) | Ultrasonic diagnostic system | |
| EP4055413B1 (en) | An ultrasound imaging catheter | |
| JPH02167151A (en) | Ultrasonic diagnostic apparatus of color flow mapping system | |
| JPH0433648A (en) | Ultrasonic diagnostic device | |
| JPH0710728Y2 (en) | Doppler tomographic ultrasound system | |
| JPH04183459A (en) | Ultrasonic diagnostic device | |
| JP3028163B2 (en) | Doppler CFM ultrasound 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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180803 |