CN110338795A - A kind of radial direction Golden Angle mr cardiac film imaging method, device and equipment - Google Patents
A kind of radial direction Golden Angle mr cardiac film imaging method, device and equipment Download PDFInfo
- Publication number
- CN110338795A CN110338795A CN201910625835.9A CN201910625835A CN110338795A CN 110338795 A CN110338795 A CN 110338795A CN 201910625835 A CN201910625835 A CN 201910625835A CN 110338795 A CN110338795 A CN 110338795A
- Authority
- CN
- China
- Prior art keywords
- image
- network
- space data
- data
- frequency domain
- 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
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/05—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves
- A61B5/055—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7225—Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7253—Details of waveform analysis characterised by using transforms
- A61B5/7257—Details of waveform analysis characterised by using transforms using Fourier transforms
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Signal Processing (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Psychiatry (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Mathematical Physics (AREA)
- Radiology & Medical Imaging (AREA)
- Power Engineering (AREA)
- High Energy & Nuclear Physics (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The embodiment of the invention discloses a kind of radial Golden Angle mr cardiac film imaging method, device and equipment.Wherein, method includes: to obtain the magnetic resonance K space data of the radial Golden Angle sampling of the default port number of target object；Permutatation is carried out to the K space data and obtains default frame number lack sampling K space data；The default frame number lack sampling K space data is input to cross-domain image reconstruction network simultaneously, to obtain target image.The embodiment of the present invention solves the problems, such as that time-consuming based on radial Golden Angle sampled data progress image reconstruction process；It may be implemented to shorten the time for carrying out the cardiac magnetic resonance data sampled based on radial Golden Angle image reconstruction, and promote the quality of reconstruction image.
Description
Technical field
The present embodiments relate to medical imaging technology more particularly to a kind of radial Golden Angle mr cardiac film imagings
Method, apparatus and equipment.
Background technique
The imaging of mr cardiac film is a kind of imaging technique of non-intrusion type, can be used in evaluation of cardiac function, locular wall fortune
Dynamic exception etc., provides information abundant for heart clinical diagnosis.However, due to magnetic resonance physics and hardware and heart movement week
The restriction of phase duration, often time and spatial resolution are limited for the imaging of mr cardiac film, can not accurate evaluation part of heart
Disease, such as the heart function situation of heart murmur.Therefore, it under the premise of guaranteeing image quality, is mentioned using fast imaging method
The time of high magnetic resonance cine cardiac imaging and spatial resolution are highly important.
Currently, the method for common accelerating magnetic resonance cine cardiac imaging, including parallel imaging (Parallel
Imaging, PI) and compressed sensing (Compressed Sensing, CS) technology, the space letter of data is utilized in such method
Breath, to fill the K space data for owing to adopt.In order to obtain higher acceleration multiple, combine the sparse sense of compressed sensing and parallel imaging
Know that technology is suggested.Later, this thought was extended to radial Golden Angle sampling configuration by the sparse concurrent technique of radial Golden Angle
Under, and be successfully applied in and freely breathe Abdominal MRI imaging, the magnetic resonance imaging of children's body, breast magnetic resonance imaging, neck magnetic
The numerous areas such as resonance image-forming.However, the radial sparse concurrent technique of Golden Angle still has a degree of motion blur, especially
It is in patient or older.Motion state dimension-sparse concurrent technique of radial direction Golden Angle rebuilds motion state, effectively
Ground alleviates motion blur.
But motion state dimension-sparse concurrent technique of radial direction Golden Angle handles the data frame after permutatation frame by frame,
Imaging process is slower, and time-consuming.
Summary of the invention
The embodiment of the present invention provides a kind of radial Golden Angle mr cardiac film imaging method, device and equipment, with reality
Now shorten the time that the cardiac magnetic resonance data sampled based on radial Golden Angle are carried out with image reconstruction, and promotes reconstruction image
Quality.
In a first aspect, the embodiment of the invention provides a kind of radial Golden Angle mr cardiac film imaging method, the party
Method includes:
Obtain the magnetic resonance K space data of the radial Golden Angle sampling of the default port number of target object；
Permutatation is carried out to the K space data and obtains default frame number lack sampling K space data；
The default frame number lack sampling K space data is input to cross-domain image reconstruction network simultaneously, to obtain target
Image.
Second aspect, the embodiment of the invention also provides a kind of radial Golden Angle mr cardiac film imaging devices, should
Device includes:
The magnetic resonance K of data acquisition module, the radial Golden Angle sampling of the default port number for obtaining target object is empty
Between data；
Data preprocessing module obtains the default space frame number lack sampling K number for carrying out permutatation to the K space data
According to；
Image reconstruction module intersects area image weight for the default frame number lack sampling K space data to be input to simultaneously
Establishing network, to obtain target image.
The third aspect, the embodiment of the invention also provides a kind of magnetic resonance scanning system, the magnetic resonance scanning system packet
It includes: scanning device, therapeutic bed and computer equipment；
Wherein, the computer equipment includes:
Memory, processor and storage are in the memory and the computer journey that can run on the processor
Sequence, the processor realize the radial Golden Angle magnetic resonance heart described in any embodiment of the present invention when executing the computer program
Dirty film imaging method.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer
Program realizes the radial Golden Angle mr cardiac electricity as described in any in inventive embodiments when described program is executed by processor
Shadow imaging method.
The embodiment of the present invention is total by the magnetic that the radial Golden Angle of the default port number to the target object got samples
Vibration K space data is rearranged, and is obtained default frame number lack sampling K space data, is then inputted lack sampling K space data
Into cross-domain image reconstruction network, target image after being rebuild is solved and is sampled in the prior art to radial Golden Angle
MR data carry out image reconstruction the problem of taking a long time；It may be implemented to shorten the heart to sampling based on radial Golden Angle
MR data carries out the time of image reconstruction, and promotes the quality of reconstruction image.
Detailed description of the invention
Fig. 1 is the flow chart of the radial Golden Angle mr cardiac film imaging method in the embodiment of the present invention one；
Fig. 2 is the radial Golden Angle acquisition trajectories schematic diagram in the embodiment of the present invention one；
Fig. 3 is that the fork area image in the embodiment of the present invention one rebuilds schematic network structure；
Fig. 4 is the topology example figure of the first frequency domain sub-network in the embodiment of the present invention one；
Fig. 5 is the topology example figure of the second frequency domain sub-network in the embodiment of the present invention one；
Fig. 6 is the structural schematic diagram of the radial Golden Angle mr cardiac film imaging device in the embodiment of the present invention two；
Fig. 7 is the structural schematic diagram of the magnetic resonance system in the embodiment of the present invention three；
Fig. 8 is the structural schematic diagram of computer equipment in magnetic resonance system in the embodiment of the present invention three.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limiting the invention.It also should be noted that in order to just
Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
Embodiment one
Fig. 1 is the flow chart for the radial Golden Angle mr cardiac film imaging method that the embodiment of the present invention one provides, this
Embodiment is applicable to the case where imaging of mr cardiac film is carried out according to radial Golden Angle sampled data, and this method can be by
Radial Golden Angle mr cardiac film imaging device realization, specifically can be by the software and/or hardware in electronic equipment come real
It applies, wherein electronic equipment can be magnetic resonance scanner.
As shown in Figure 1, radial Golden Angle mr cardiac film imaging method specifically includes:
S110, obtain target object default port number radial Golden Angle sampling magnetic resonance K space data.
Wherein, target object can be people either animal, when it needs to carry out heart disease diagnosis or heart function
When can assess, then become the scanning target object of magnetic resonance scanner.
When magnetic resonance scanner acquires data, it will usually which multiple coils acquire data simultaneously, to obtain target object not
With the cardiac magnetic resonance data of angle, number of coils is determined according to the setting of magnetic resonance scanner.Specifically, multiple coils pair
Multiple channels are answered, i.e., magnetic resonance scanner acquisition is multichannel K space data, and K is also Fourier space in space, is that band is free
Between location coding information magnetic resonance signal initial numberical data filling space, each width magnetic resonance image has it corresponding
K space data dot matrix.When acquisition data are in the sampled data of radial gold angle, then target object can be obtained
The magnetic resonance K space data of the radial Golden Angle sampling of default port number.
In radial acquisitions, sample track is usually to ask since the center of k-space to k-space edge, or from k sky
An edge start diametrically to carry out until another edge, in this application, by taking second of sample track as an example into
Row explanation.The data acquisition trajectories of radial gold angular direction can refer to radial Golden Angle acquisition trajectories schematic diagram shown in Fig. 2, diameter
111.25 degree of fixed angle are rotated every time to Golden Angle acquisition, this numerical value is calculated based on golden section proportion,
Therefore referred to as Golden Angle.The benefit of radial Golden Angle acquisition data be so that the k-space of any time in sampling process all
It shows and samples relatively uniform state, this carries out image reconstruction for the data using any amount sampling line.
S120, default frame number lack sampling K space data is obtained to K space data progress permutatation.
Specifically, carrying out permutatation to K space data obtains default frame number lack sampling K space data, can be the K
Spatial data is distributed equally, and making every frame lack sampling K space data includes the corresponding space the K number of identical vector sample line
According to.Illustratively, it is assumed that have 256 sampled datas on every sampling line, sample the sampled data of line in a manner of arranging for every
It is arranged, a total of 1000 samplings line, then all sampled datas after arrangement have 256*1000 data, if with
The data of every 20 samplings line are split to obtain the K space data of lack sampling, then deficient the adopting of available 50 frame 256*20
Sample K space data.
In another preferred embodiment, permutatation is carried out to K space data and obtains the default space frame number lack sampling K
Data can also be and be divided into the K space data is heterogeneous default frame number according to the motion state of the target object and owe
K space data is sampled, the motion state includes the respiratory rate or palmic rate of the target object.For example, in acquisition number
During, the heart of target object can carry out contraction and diastole with the rhythm of breathing, if there is 30 sampling line numbers evidences to be
Collected in heart contraction, 20 sampling line numbers are according to being collected in diastole, then can be first with 256*30
Data arrangement be a frame lack sampling K space data, then with the data arrangement of 256*20 be a frame lack sampling K space data, so
After repeat above-mentioned data arrangement process, until obtaining all lack sampling K space data.According to target object to motion state
Data permutation is carried out, the noises such as image artifacts caused by motion blur are effectively alleviated.
S130, the default frame number lack sampling K space data is input to cross-domain image reconstruction network simultaneously, to obtain
Target image.
Specifically, cross-domain image reconstruction network includes: frequency domain network and image area sub-network, wherein the frequency
Rate domain sub-network includes first frequency domain sub-network and second frequency domain sub-network.The specific structure of cross-domain image reconstruction network
It can refer to Fig. 3.
Mainly included the following steps: by the image reconstruction process of cross-domain image reconstruction network firstly, by described default
Frame number lack sampling K space data is input to first frequency domain sub-network according to the first preset format, obtains the default frame number and owes
Fisrt feature information of the K space data on channel-space is sampled, meanwhile, the default frame number lack sampling K space data is pressed
Be input to second frequency domain sub-network according to the second preset format, obtain the default frame number lack sampling K space data when m- sky
Between on second feature information.Wherein, K1 is the lack sampling K Space format of the first preset format, and the first preset format is
(kt, kx, ky, coil), it is therefore an objective to allow first frequency domain sub-network to carry out convolution in (kx, ky, coil) dimension, so that first
Frequency domain network extracts channel-spatial information.K2 is the lack sampling K Space format of the second preset format, the second default lattice
Formula is (coil, kx, ky, kt), it is therefore an objective to allow second frequency domain sub-network to carry out convolution in (kx, ky, kt) dimension, so that the
Two frequency domain network extraction times-spatial information.Two sub-networks can be made independently to learn the spy on different dimensions in this way
Sign, is conducive to the correlation for fully exploring parallel heart dynamic data, mining data is in space, time and interchannel as far as possible
Redundancy.
Specifically, the usable residual error density network of first frequency domain sub-network (Residual Dense Network,
RDN), which can be as shown in Figure 4.The feature of network maximum is can to merge the part of different depth and the overall situation
Feature, so that the feature of whole network is effectively utilized.Residual error density network is mainly made of five major parts, respectively
It is: 1) shallow-layer feature extraction；2) residual error density module (Residual Dense Block, RDB) is used for Local Feature Fusion；3)
Global characteristics fusion；4) global residual error study；5) further feature is extracted.
The forward process of first frequency domain sub-network is as follows:
0th step --- input: it owes to adopt multichannel K space data, K space data dimension is (kt, kx, ky, coil).By K sky
Between data dimension be set as (kt, kx, ky, coil) 3D convolutional layer can be made to carry out convolution on (kx, ky, coil), that is, make
Obtain book e-learning channel-space characteristics.
Step 1 --- shallow-layer feature extraction: it is made of two 3D convolutional layers.It owes to adopt multichannel K space data and passes through this first
Two convolutional layers carry out shallow-layer feature extraction.
Step 2 --- Local Feature Fusion: it is made of D residual error density module.There are several in each residual error density module
3D convolutional layer.Unlike common convolutional layer, the output of each convolutional layer is not only inputted into next convolutional layer, inputs simultaneously
To the subsequent all convolutional layers of RDB, component density connection.The purpose of density connection is: so that deep layer convolutional layer and shallow-layer convolutional layer
Play a role.Again together by the output connection (concatenate) of these 3D convolutional layers, and by the volume of a 1*1*1
Lamination carries out Fusion Features.In this way, just completing the Fusion Features of a density network.It is connected using a residual error, just
The output of residual error density module is arrived.Since each residual error density module belongs to a part of entire frequency domain network, because
This Fusion Features herein, and it is known as Local Feature Fusion.Wherein, D is the integer greater than zero
Step 3 --- global characteristics fusion: together by the output connection (concatenate) of D residual error density module,
Using the convolutional layer of a 1*1*1, the result of global characteristics fusion can be obtained.
Step 4 --- the fused result of step 3 global characteristics global residual error study: is passed through into a 3D convolutional layer and one
A residual error connection carries out global residual error study.
Step 5 --- further feature is extracted: being made of two 3D convolutional layers.After the study of global residual error as a result, using 2
A 3D convolutional layer carries out further feature extraction.
Step 6 --- the multichannel K space data (channel-space extracted of first frequency domain network reconnection of output
Information, fisrt feature information).
The multichannel K space data of reconstruction is subjected to inverse Fourier transform (IFFT) again, obtains multichannel image.Multichannel
Image can obtain single channel image (i.e. the first reconstruction image) after (coil combination) is merged in channel, use
In the feature extraction of image area network.The specific practice of channel fusion may is that its channel susceptibility of multichannel image dot product
Conjugation, and sum in channel direction.
It is the topology example figure of second frequency domain sub-network, M convolution of second frequency domain Web vector graphic as shown in Figure 5
Module (i.e. frequency domain module) cascades.Specifically, second frequency domain sub-network includes M frequency domain module (Fnetm, m=
1 ..., M), each frequency domain module includes L 3 dimension convolutional layer (3D Conv) and the consistent layer (Kspace of a frequency domain data
Data Consistency, KDC).The input of second frequency domain sub-network is the multichannel K space data for owing to adopt, by K space dimension
Degree, which is set as (coil, kx, ky, kt), can make 3D convolutional layer carry out convolution on (kx, ky, kt), that is, so that this sub-network
Learning time-space characteristics.The forward process of second frequency domain sub-network can be indicated by following formula:
First frequency domain module (m=1):
Subsequent frequency domain module (m=2 ..., M):
Wherein, KDC is for executing frequency domain data coherency operation:
It is the convolution kernel and bias term of first of convolutional layer in m-th of frequency domain module respectively；L=
1,…,L；M=1 ..., M；It is the output of first of convolutional layer in m-th of frequency domain module.In addition to the last one convolution
Layer, remaining all convolutional layer are activated by nonlinear function δ.After convolutional layer extracts feature, frequency domain is utilized
The consistent layer of data corrects the space K of neural network forecast,It is pairThe result corrected.Enable all K acquired empty
Between coordinate constitute collection be combined into Ω.If K space coordinate (kx,ky) in set omega, thenIt will be empty by the K really acquired
Between point corrected.Actual samples point, if λ → ∞, directly can be gone to substitute by λ for controlling the consistent degree of dataCorresponding point.Wherein, the embodiment of the present application takes λ → ∞.KuFor a K space data of frequency domain network processes.
Sub-network final output in second frequency domain isIt is rightIt carries out inverse Fourier transform and channel is melted
It closes, single channel image data (i.e. the second reconstruction image) can be obtained.
Then, first reconstruction image and the second reconstruction image are merged, and fused image is input to described
Image area sub-network；The image characteristic of field of the fused image is extracted by described image domain sub-network, and obtains target
Image.
Optionally, described image domain network includes N number of image area module, and each image area module includes L Three dimensional convolution
Layer, a residual error connect layer consistent with an image domain data, wherein N is the integer greater than zero, and L is the integer greater than zero.
In the embodiment of the present application, image area network can refer to DC-CNN structure.The forward process of image area network can
It is indicated by following formula:
Subsequent image area module (n=2 ..., N):
Wherein, image domain data consistency (Image Data Consistency, IDC) is for executing image domain data one
Cause operation:
It is the convolution kernel and bias term of first of convolutional layer in the module of n-th image domain, l=respectively
1,…,L；N=1 ..., N；It is the output of first of convolutional layer in the module of n-th image domain.In addition to the last one convolutional layer,
Remaining all convolutional layer is activated by nonlinear function δ.After convolutional layer extracts feature, residual error study is introduced,
SnIt is the result of residual error study.To SnIt carries out image domain data coherency operation (IDC).Compared to KDC, IDC more frequency domain and images
It is converted between domain.It is to SnImage after carrying out IDC.
The technical solution of the present embodiment is sampled by the radial Golden Angle of the default port number to the target object got
Magnetic resonance K space data rearranged, default frame number lack sampling K space data is obtained, then by the space lack sampling K number
According to being input in cross-domain image reconstruction network, the target image after being rebuild, solve in the prior art to radial Huang
The MR data of Jin Jiao sampling carries out the problem of image reconstruction takes a long time；It may be implemented to shorten and be adopted to based on radial Golden Angle
The cardiac magnetic resonance data of sample carry out the time of image reconstruction, and promote the quality of reconstruction image.
Embodiment two
Fig. 6 is a kind of structural representation for radial Golden Angle mr cardiac film imaging device that inventive embodiments two provide
Figure, the present embodiment are applicable to the case where imaging of mr cardiac film is carried out according to radial Golden Angle sampled data, the device
It is configured in magnetic resonance scanner.
As shown in fig. 6, the radial Golden Angle mr cardiac film imaging device provided in the embodiment of the present invention includes: number
According to acquisition module 610, data preprocessing module 620 and image reconstruction module 630.
Wherein, data acquisition module 610, the magnetic of the radial Golden Angle sampling of the default port number for obtaining target object
Resonate K space data；Data preprocessing module 620 owes to adopt for obtaining default frame number to K space data progress permutatation
Sample K space data；Image reconstruction module 630, for the default frame number lack sampling K space data to be input to cross-domain simultaneously
Image reconstruction network, to obtain target image.
The technical solution of the embodiment of the present invention passes through the radial Golden Angle of the default port number to the target object got
The magnetic resonance K space data of sampling is rearranged, and default frame number lack sampling K space data is obtained, then that lack sampling K is empty
Between data be input in cross-domain image reconstruction network, the target image after being rebuild, the diameter in the prior art solved
The MR data sampled to Golden Angle carries out the problem of image reconstruction takes a long time；It may be implemented to shorten to based on radial gold
The cardiac magnetic resonance data of angle sampling carry out the time of image reconstruction, and promote the quality of reconstruction image.
Optionally, data preprocessing module 620 is specifically used for:
The K space data is distributed equally, making every frame lack sampling K space data includes identical vector sample line pair
The K space data answered.
Optionally, data preprocessing module 620 can also be used in:
It is divided into default frame number lack sampling K for the K space data is heterogeneous according to the motion state of the target object
Spatial data, the motion state include the respiratory rate or palmic rate of the target object.
Further, the cross-domain image reconstruction network includes: frequency domain network and image area sub-network, wherein
The frequency domain network includes first frequency domain sub-network and second frequency domain sub-network.
Correspondingly, image reconstruction module 630 is specifically used for:
The default frame number lack sampling K space data is input to first frequency domain sub-network according to the first preset format,
Fisrt feature information of the default frame number lack sampling K space data on channel-space is obtained, meanwhile, by the default frame
Frequent yawning samples K space data and is input to the and frequency domain network according to the second preset format, obtains the default frame number and owes to adopt
Second feature information of the sample K space data on time-space；
Image reconstruction is carried out according to the fisrt feature information and the second feature information respectively and obtains the first reconstruction figure
Picture and the second reconstruction image；
First reconstruction image and the second reconstruction image are merged, and fused image is input to described image domain
Sub-network；
The image characteristic of field of the fused image is extracted by described image domain sub-network, and obtains target image.
Optionally, first frequency domain sub-network is residual error density network, and second frequency domain sub-network includes M
Frequency domain module, each frequency domain module include L Three dimensional convolution layer and the consistent layer of a frequency domain data, wherein M for greater than
Zero integer, L are the integer greater than zero.
Optionally, described image domain network includes N number of image area module, and each image area module includes L Three dimensional convolution
Layer, a residual error connect layer consistent with an image domain data, wherein N is the integer greater than zero, and L is the integer greater than zero.
The executable present invention of radial direction Golden Angle mr cardiac film imaging device provided by the embodiment of the present invention is any
Radial direction Golden Angle mr cardiac film imaging method provided by embodiment has the corresponding functional module of execution method and has
Beneficial effect.
Embodiment three
Fig. 7 is the structural schematic diagram of the magnetic resonance scanning system in the embodiment of the present invention three, the magnetic resonance scanning system
It include: scanning device, therapeutic bed and computer equipment.
Wherein, scanning device is for obtaining magnetic resonance scanning data；Therapeutic bed user carries the mesh for receiving magnetic resonance imaging
Object is marked, and moves target object to this invisible scanning position；Computer equipment is then used to control scanning device and therapeutic bed
The course of work, to complete magnetic resonance imaging, it may also be used for obtain magnetic resonance scanning data and data are handled, obtain weight
Build target image.
Further, the hardware structural diagram of computer equipment, can refer to Fig. 8.
Fig. 8 is the structural schematic diagram of the computer equipment in the embodiment of the present invention three.Fig. 8, which is shown, to be suitable for being used to realizing this
The block diagram of the exemplary computer device 812 of invention embodiment.The computer equipment 812 that Fig. 8 is shown is only an example,
Should not function to the embodiment of the present invention and use scope bring any restrictions.As shown in figure 8, computer equipment 812 is with general
Calculate the form performance of equipment.The component of computer equipment 812 can include but is not limited to: one or more processor or
Processing unit 816, system storage 828 connect different system components (including system storage 828 and processing unit 816)
Bus 818.
Bus 818 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts
For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC)
Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Computer equipment 812 typically comprises a variety of computer system readable media.These media can be it is any can
The usable medium accessed by computer equipment 812, including volatile and non-volatile media, moveable and immovable Jie
Matter.
System storage 828 may include the computer system readable media of form of volatile memory, such as deposit at random
Access to memory (RAM) 830 and/or cache memory 832.Computer equipment 812 may further include it is other it is removable/
Immovable, volatile/non-volatile computer system storage medium.Only as an example, storage system 834 can be used for reading
Write immovable, non-volatile magnetic media (Fig. 8 do not show, commonly referred to as " hard disk drive ").Although being not shown in Fig. 8,
The disc driver for reading and writing to removable non-volatile magnetic disk (such as " floppy disk ") can be provided, and non-easy to moving
The CD drive that the property lost CD (such as CD-ROM, DVD-ROM or other optical mediums) is read and write.In these cases, each
Driver can be connected by one or more data media interfaces with bus 818.Memory 828 may include at least one
Program product, the program product have one group of (for example, at least one) program module, these program modules are configured to perform this
Invent the function of each embodiment.
Program/utility 840 with one group of (at least one) program module 842, can store in such as memory
In 828, such program module 842 includes but is not limited to operating system, one or more application program, other program modules
And program data, it may include the realization of network environment in each of these examples or certain combination.Program module 842
Usually execute the function and/or method in embodiment described in the invention.
Computer equipment 812 can also be with one or more external equipments 814 (such as keyboard, sensing equipment, display
824 etc.) communicate, wherein display 824 is displayed for the corresponding information of digitized x-ray camera system, and provide with it is described
The entrance of digitized x-ray camera system interaction.Computer equipment 812 can also enable a user to and the calculating with one or more
The equipment communication of the interaction of machine equipment 812, and/or with enable the computer equipment 812 and one or more of the other calculating equipment
Any equipment (such as network interface card, modem etc.) communication communicated.This communication can pass through input/output (I/
O) interface 822 carries out.Also, computer equipment 812 can also pass through network adapter 820 and one or more network (example
Such as local area network (LAN), wide area network (WAN) and/or public network, such as internet) communication.As shown, network adapter 820
It is communicated by bus 818 with other modules of computer equipment 812.It should be understood that although being not shown in Fig. 8, it can be in conjunction with meter
It calculates machine equipment 812 and uses other hardware and/or software module, including but not limited to: microcode, device driver, redundancy processing
Unit, external disk drive array, RAID system, tape drive and data backup storage system etc..
Processing unit 816 by the program that is stored in system storage 828 of operation, thereby executing various function application with
And data processing, such as realize radial direction Golden Angle mr cardiac film imaging method provided by the embodiment of the present invention, the party
Method specifically includes that
Obtain the magnetic resonance K space data of the radial Golden Angle sampling of the default port number of target object；
Permutatation is carried out to the K space data and obtains default frame number lack sampling K space data；
The default frame number lack sampling K space data is input to cross-domain image reconstruction network simultaneously, to obtain target
Image.
Example IV
The embodiment of the present invention four additionally provides a kind of computer readable storage medium, is stored thereon with computer program, should
The radial direction Golden Angle mr cardiac film imaging method as provided by the embodiment of the present invention is realized when program is executed by processor,
This method specifically includes that
Obtain the magnetic resonance K space data of the radial Golden Angle sampling of the default port number of target object；
Permutatation is carried out to the K space data and obtains default frame number lack sampling K space data；
The default frame number lack sampling K space data is input to cross-domain image reconstruction network simultaneously, to obtain target
Image.
The computer storage medium of the embodiment of the present invention, can be using any of one or more computer-readable media
Combination.Computer-readable medium can be computer-readable signal media or computer readable storage medium.It is computer-readable
Storage medium for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device or
Device, or any above combination.The more specific example (non exhaustive list) of computer readable storage medium includes: tool
There are electrical connection, the portable computer diskette, hard disk, random access memory (RAM), read-only memory of one or more conducting wires
(ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-
ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer-readable storage
Medium can be any tangible medium for including or store program, which can be commanded execution system, device or device
Using or it is in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
Further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion
Divide and partially executes or executed on a remote computer or server completely on the remote computer on the user computer.?
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or
Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as mentioned using Internet service
It is connected for quotient by internet).
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (10)
1. a kind of radial direction Golden Angle mr cardiac film imaging method characterized by comprising
Obtain the magnetic resonance K space data of the radial Golden Angle sampling of the default port number of target object；
Permutatation is carried out to the K space data and obtains default frame number lack sampling K space data；
The default frame number lack sampling K space data is input to cross-domain image reconstruction network simultaneously, to obtain target image.
2. the method according to claim 1, wherein carrying out permutatation to the K space data obtains default frame
Frequent yawning samples K space data, comprising:
The K space data is distributed equally, making every frame lack sampling K space data includes that identical vector sample line is corresponding
The K space data.
3. the method according to claim 1, wherein carrying out permutatation to the K space data obtains default frame
Frequent yawning samples K space data, comprising:
It is divided into the default space frame number lack sampling K for the K space data is heterogeneous according to the motion state of the target object
Data, the motion state include the respiratory rate or palmic rate of the target object.
4. the method according to claim 1, wherein the cross-domain image reconstruction network includes: frequency domain
Network and image area sub-network, wherein the frequency domain network includes first frequency domain sub-network and second frequency domain subnet
Network.
5. according to the method described in claim 4, it is characterized in that, the default frame number lack sampling K space data is defeated simultaneously
Enter to area image reconstruction network is intersected, to obtain target image, comprising:
The default frame number lack sampling K space data is input to first frequency domain sub-network according to the first preset format, is obtained
Fisrt feature information of the default frame number lack sampling K space data on channel-space, meanwhile, the default frame number is owed
It samples K space data and is input to second frequency domain sub-network according to the second preset format, it is empty to obtain the default frame number lack sampling K
Between second feature information of the data on time-space；
Respectively according to the fisrt feature information and the second feature information carry out image reconstruction obtain the first reconstruction image and
Second reconstruction image；
First reconstruction image and the second reconstruction image are merged, and fused image is input to described image domain subnet
Network；
The image characteristic of field of the fused image is extracted by described image domain sub-network, and obtains target image.
6. method according to claim 4 or 5, it is characterised in that first frequency domain sub-network is residual error density net
Network, second frequency domain sub-network include M frequency domain module, and each frequency domain module includes L Three dimensional convolution layer and one
The consistent layer of a frequency domain data, wherein M is the integer greater than zero, and L is the integer greater than zero.
7. method according to claim 4 or 5, which is characterized in that described image domain network includes N number of image area module,
Each image area module includes L Three dimensional convolution layer, residual error connection layer consistent with an image domain data, wherein N is big
In zero integer, L is the integer greater than zero.
8. a kind of radial direction Golden Angle mr cardiac film imaging device characterized by comprising
Data acquisition module, the space the magnetic resonance K number of the radial Golden Angle sampling of the default port number for obtaining target object
According to；
Data preprocessing module obtains default frame number lack sampling K space data for carrying out permutatation to the K space data；
Image reconstruction module, for the default frame number lack sampling K space data to be input to cross-domain image reconstruction net simultaneously
Network, to obtain target image.
9. a kind of magnetic resonance scanning system, the magnetic resonance scanning system include:
Scanning device, therapeutic bed and computer equipment；
Wherein, the computer equipment include: memory, processor and storage in the memory and can be in the processing
The computer program run on device, which is characterized in that the processor realizes such as claim 1 when executing the computer program
To any one of 7 radial Golden Angle mr cardiac film imaging methods.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In realization radial Golden Angle magnetic resonance heart as described in any one of claim 1 to 7 when the computer program is executed by processor
Dirty film imaging method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910625835.9A CN110338795B (en) | 2019-07-11 | 2019-07-11 | Radial golden angle magnetic resonance heart film imaging method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910625835.9A CN110338795B (en) | 2019-07-11 | 2019-07-11 | Radial golden angle magnetic resonance heart film imaging method, device and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110338795A true CN110338795A (en) | 2019-10-18 |
| CN110338795B CN110338795B (en) | 2023-09-01 |
Family
ID=68175129
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910625835.9A Active CN110338795B (en) | 2019-07-11 | 2019-07-11 | Radial golden angle magnetic resonance heart film imaging method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110338795B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110827369A (en) * | 2019-10-31 | 2020-02-21 | 上海联影智能医疗科技有限公司 | Undersampling model generation method, image reconstruction method, device and storage medium |
| CN111080738A (en) * | 2019-11-28 | 2020-04-28 | 上海联影智能医疗科技有限公司 | System and method for image reconstruction |
| CN111145875A (en) * | 2019-12-27 | 2020-05-12 | 上海联影医疗科技有限公司 | Data analysis system |
| CN111273207A (en) * | 2020-01-22 | 2020-06-12 | 上海东软医疗科技有限公司 | Magnetic resonance imaging method, magnetic resonance imaging apparatus, electronic device, and storage medium |
| CN113296038A (en) * | 2020-02-24 | 2021-08-24 | 上海联影医疗科技股份有限公司 | Magnetic resonance imaging system and method based on K-space radial sampling |
| CN113592972A (en) * | 2021-07-30 | 2021-11-02 | 哈尔滨工业大学（深圳） | Magnetic resonance image reconstruction method and device based on multi-modal aggregation |
| CN113866695A (en) * | 2021-10-12 | 2021-12-31 | 上海交通大学 | Image acquisition and reconstruction method and system for magnetic resonance real-time guidance intervention |
| CN115067945A (en) * | 2022-08-22 | 2022-09-20 | 深圳市海清视讯科技有限公司 | Fatigue detection method, device, equipment and storage medium |
| CN117054943A (en) * | 2023-10-11 | 2023-11-14 | 山东奥新医疗科技有限公司 | Magnetic resonance imaging method, device, equipment and medium based on radial basis network |
| US11880915B2 (en) | 2019-08-26 | 2024-01-23 | Shanghai United Imaging Intelligence Co., Ltd. | Systems and methods for magnetic resonance imaging |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150077112A1 (en) * | 2012-04-19 | 2015-03-19 | New York University | System, method and computer-accessible medium for highly-accelerated dynamic magnetic resonance imaging using golden-angle radial sampling and compressed sensing |
-
2019
- 2019-07-11 CN CN201910625835.9A patent/CN110338795B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150077112A1 (en) * | 2012-04-19 | 2015-03-19 | New York University | System, method and computer-accessible medium for highly-accelerated dynamic magnetic resonance imaging using golden-angle radial sampling and compressed sensing |
| US20190064296A1 (en) * | 2012-04-19 | 2019-02-28 | New York University | System, method and computer-accessible medium for highly-accelerated dynamic magnetic resonance imaging using golden-angle radial sampling and compressed sensing |
Non-Patent Citations (2)
| Title |
|---|
| SHANSHAN WANG,ET AL: "DIMENSION:Dynamic MR Imaging with Both K-space and Spatial Prior Knowledge Obtained via Multi-Supervised Network Training", 《ARXIV》 * |
| TAEJOON EO,ET AL: "KIKI-net:cross-domain convolutional neural networks for reconstructing undersampled magnetic resonance images", 《MAGNETIC RESONANCE IN MEDICINE》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11880915B2 (en) | 2019-08-26 | 2024-01-23 | Shanghai United Imaging Intelligence Co., Ltd. | Systems and methods for magnetic resonance imaging |
| CN110827369A (en) * | 2019-10-31 | 2020-02-21 | 上海联影智能医疗科技有限公司 | Undersampling model generation method, image reconstruction method, device and storage medium |
| CN110827369B (en) * | 2019-10-31 | 2023-09-26 | 上海联影智能医疗科技有限公司 | Undersampling model generation method, image reconstruction method, apparatus and storage medium |
| CN111080738A (en) * | 2019-11-28 | 2020-04-28 | 上海联影智能医疗科技有限公司 | System and method for image reconstruction |
| CN111080738B (en) * | 2019-11-28 | 2024-02-27 | 上海联影智能医疗科技有限公司 | System and method for image reconstruction |
| CN111145875B (en) * | 2019-12-27 | 2023-05-12 | 上海联影医疗科技股份有限公司 | Data analysis system |
| CN111145875A (en) * | 2019-12-27 | 2020-05-12 | 上海联影医疗科技有限公司 | Data analysis system |
| CN111273207A (en) * | 2020-01-22 | 2020-06-12 | 上海东软医疗科技有限公司 | Magnetic resonance imaging method, magnetic resonance imaging apparatus, electronic device, and storage medium |
| CN113296038B (en) * | 2020-02-24 | 2022-11-25 | 上海联影医疗科技股份有限公司 | Magnetic resonance imaging system and method based on K-space radial sampling |
| CN113296038A (en) * | 2020-02-24 | 2021-08-24 | 上海联影医疗科技股份有限公司 | Magnetic resonance imaging system and method based on K-space radial sampling |
| CN113592972B (en) * | 2021-07-30 | 2023-11-14 | 哈尔滨工业大学（深圳） | Magnetic resonance image reconstruction method and device based on multi-mode aggregation |
| CN113592972A (en) * | 2021-07-30 | 2021-11-02 | 哈尔滨工业大学（深圳） | Magnetic resonance image reconstruction method and device based on multi-modal aggregation |
| CN113866695A (en) * | 2021-10-12 | 2021-12-31 | 上海交通大学 | Image acquisition and reconstruction method and system for magnetic resonance real-time guidance intervention |
| CN115067945A (en) * | 2022-08-22 | 2022-09-20 | 深圳市海清视讯科技有限公司 | Fatigue detection method, device, equipment and storage medium |
| CN117054943A (en) * | 2023-10-11 | 2023-11-14 | 山东奥新医疗科技有限公司 | Magnetic resonance imaging method, device, equipment and medium based on radial basis network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110338795B (en) | 2023-09-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110338795A (en) | A kind of radial direction Golden Angle mr cardiac film imaging method, device and equipment | |
| CN110031786A (en) | MR image reconstruction method, MR imaging method, equipment and medium | |
| CN111368849B (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| CN109009200A (en) | System and method for positron emission tomography image reconstruction | |
| CN101023886A (en) | Method for the graphical representation of a medical instrument inserted at least partially into an object under examination | |
| CN109239631A (en) | A kind of MR imaging method and device | |
| CN111369675B (en) | Three-dimensional visual model reconstruction method and device based on lung nodule pleural projection | |
| CN107865659A (en) | MR imaging apparatus and the method for obtaining MRI | |
| KR102108418B1 (en) | Method for providing an image based on a reconstructed image group and an apparatus using the same | |
| CN106456046A (en) | Method of improved multiple-phase dynamic contrast-enhanced magnetic resonance imaging | |
| JP5029702B2 (en) | Image generating apparatus, image generating method, and program | |
| CN104887257A (en) | Image processing device | |
| KR101919908B1 (en) | Method for facilitating labeling of medical image and apparatus using the same | |
| CN110007258A (en) | A kind of method and device of the receiving coil position of determining magnetic resonance system | |
| Franson et al. | A system for real-time, online mixed-reality visualization of cardiac magnetic resonance images | |
| CN110718284A (en) | Three-dimensional medical image data interaction method and system | |
| CN115965837A (en) | Image reconstruction model training method, image reconstruction method and related equipment | |
| CN110325871A (en) | System and method for image reconstruction | |
| Zhang et al. | MR and ultrasound cardiac image dynamic visualization and synchronization over Internet for distributed heart function diagnosis | |
| CN109069059A (en) | For the system and method to mobile main body imaging | |
| CN103860173B (en) | Method and device for reconstructing magnetic resonance k space and magnetic resonance imaging method and device | |
| US20240062332A1 (en) | System and method for improving sharpness of magnetic resonance images using a deep learning neural network | |
| WO2023060735A1 (en) | Image generation model training and image generation methods, apparatus, device, and medium | |
| KR102275622B1 (en) | Method for providing an image based on a reconstructed image group and an apparatus using the same | |
| CN110226099A (en) | Four-dimensional MR data is acquired during object movement |
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 |