CN114236444B - Hyperpolarized gas lung variable sampling rate rapid magnetic resonance diffusion weighted imaging method - Google Patents
Hyperpolarized gas lung variable sampling rate rapid magnetic resonance diffusion weighted imaging method Download PDFInfo
- Publication number
- CN114236444B CN114236444B CN202111466215.9A CN202111466215A CN114236444B CN 114236444 B CN114236444 B CN 114236444B CN 202111466215 A CN202111466215 A CN 202111466215A CN 114236444 B CN114236444 B CN 114236444B
- Authority
- CN
- China
- Prior art keywords
- sampling
- value
- lung
- magnetic resonance
- weighted imaging
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R33/00—Arrangements or instruments for measuring magnetic variables
- G01R33/20—Arrangements or instruments for measuring magnetic variables involving magnetic resonance
- G01R33/44—Arrangements or instruments for measuring magnetic variables involving magnetic resonance using nuclear magnetic resonance [NMR]
- G01R33/48—NMR imaging systems
- G01R33/54—Signal processing systems, e.g. using pulse sequences ; Generation or control of pulse sequences; Operator console
- G01R33/56—Image enhancement or correction, e.g. subtraction or averaging techniques, e.g. improvement of signal-to-noise ratio and resolution
- G01R33/5601—Image enhancement or correction, e.g. subtraction or averaging techniques, e.g. improvement of signal-to-noise ratio and resolution involving use of a contrast agent for contrast manipulation, e.g. a paramagnetic, super-paramagnetic, ferromagnetic or hyperpolarised contrast agent
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R33/00—Arrangements or instruments for measuring magnetic variables
- G01R33/20—Arrangements or instruments for measuring magnetic variables involving magnetic resonance
- G01R33/44—Arrangements or instruments for measuring magnetic variables involving magnetic resonance using nuclear magnetic resonance [NMR]
- G01R33/48—NMR imaging systems
- G01R33/54—Signal processing systems, e.g. using pulse sequences ; Generation or control of pulse sequences; Operator console
- G01R33/56—Image enhancement or correction, e.g. subtraction or averaging techniques, e.g. improvement of signal-to-noise ratio and resolution
- G01R33/561—Image enhancement or correction, e.g. subtraction or averaging techniques, e.g. improvement of signal-to-noise ratio and resolution by reduction of the scanning time, i.e. fast acquiring systems, e.g. using echo-planar pulse sequences
- G01R33/5615—Echo train techniques involving acquiring plural, differently encoded, echo signals after one RF excitation, e.g. using gradient refocusing in echo planar imaging [EPI], RF refocusing in rapid acquisition with relaxation enhancement [RARE] or using both RF and gradient refocusing in gradient and spin echo imaging [GRASE]
-
- 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
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- High Energy & Nuclear Physics (AREA)
- Condensed Matter Physics & Semiconductors (AREA)
- General Physics & Mathematics (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The invention discloses a hyperpolarized gas lung variable sampling rate rapid magnetic resonance diffusion weighted imaging method, wherein a subject inhales hyperpolarized gas and holds breath, lung multi-b value weighted imaging data with variable sampling rate are acquired in the breath holding process, each b value of diffusion weighted imaging adopts different sampling rates, corresponding acquired K space sampling matrixes are different, and the image quality is ensured while the scanning time is shortened. And (3) carrying out image reconstruction by combining compressed sensing after data acquisition, and extracting lung microstructure parameters through a lung airway microstructure model. The method can realize quantitative assessment of the pulmonary alveolus airway microstructure without invasiveness and ionizing radiation.
Description
Technical Field
The invention belongs to the technical field of nuclear magnetic resonance imaging (Magnetic Resonance Imaging, MRI), and particularly relates to a hyperpolarized gas lung variable sampling rate rapid magnetic resonance diffusion weighted imaging method which can shorten the scanning time of magnetic resonance diffusion weighted imaging. Adapted for hyperpolarized gases, e.g. 129 Xe or 3 He or He 83 Kr imaging.
Background
The traditional magnetic resonance imaging uses water protons in a human body as a signal source, and can obtain the functional and structural information of most tissues except the lung of the human body. However, since the lungs are hollow structures, the overall water proton spin density is much lower than other tissues, and therefore the lungs are dead spots for conventional MRI. Hyperpolarized gas MRI provides a new imaging technique, and can realize visualization of lung, and determination of lung structure and function by virtue of the advantages of easy diffusion, good chemical displacement sensitivity, fat solubility and the like of gasAnd (5) evaluating the quantity. Inert gases such as 129 Xe or 3 He can become hyperpolarized gas through a spin exchange optical pump, and the magnetic resonance sensitivity of the hyperpolarized gas can be improved by 4-5 orders of magnitude compared with that of the hyperpolarized gas in a thermal equilibrium state. Diffusion weighted imaging (Diffusion WeightedImaging, DWI) can measure the Diffusion of molecules and can realize quantitative assessment of lung microstructure based on the hyperpolarized gas magnetic resonance (DWI) method. Conventional DWI scanning is long and cannot withstand long breath-hold scans for patients with pulmonary disease.
In order to shorten the scan time, techniques are continually evolving to speed up MRI data acquisition. The most widely used acceleration technique at present is compressed sensing (Compressed Sensing, CS), which exploits the inherent sparsity of MRI data to achieve accelerated acquisition of MRI by randomly undersampling K-space, and without requiring expensive hardware and complex acquisition schemes. CS has been used for the accelerated acquisition of hyperpolarized gas magnetic resonance DWI data. Currently, the field has developed a number of fast magnetic resonance methods for pulmonary diffusion weighted imaging, which generally use either a fixed acceleration factor in combination with a fixed undersampled K-space sampling matrix or a fixed acceleration factor in combination with a varying undersampled K-space sampling matrix. For a constant acceleration factor acquisition strategy, the magnitude of the acceleration factor is limited, and when it increases, undersampling acquisition of K-space inevitably causes image loss, thereby introducing artifacts in the reconstructed image.
The prior related technical proposal aiming at the application background of the invention is as follows:
1) Fixed acceleration factors and fixed K-space sampling matrices (Magnetic Resonance in Medicine,2010, 63:1059-1069). Since DWI signals decay as the b value increases, it is more difficult to accurately measure the pulmonary microstructure parameters.
2) Fixed acceleration factors and a variable K-space sampling matrix (Magnetic Resonance in Medicine,2020, 84:416-426). K space sampling matrixes corresponding to different b values are different, but the size of an acceleration factor is limited, the acceleration factor is small, and the shortened scanning time is limited; when the acceleration factor is large, the image is caused to introduce reconstruction artifacts.
Disclosure of Invention
The invention aims to solve the problems in the prior art and provides a hyperpolarized gas lung variable sampling rate rapid magnetic resonance diffusion weighted imaging method.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
the hyperpolarized gas lung variable sampling rate rapid magnetic resonance diffusion weighted imaging method comprises the following steps:
step 1, a subject inhales hyperpolarized gas, then imaging scanning is carried out in a single breath-hold, and variable acceleration factor sampling is carried out according to different acceleration factors and different sampling matrixes corresponding to different b-value setting, so that lung multi-b-value weighted imaging data with variable sampling rate are obtained;
step 2, reconstructing the lung multi-b-value weighted imaging data with the variable sampling rate obtained in the step 1 to obtain a lung reconstructed multi-b-value diffusion weighted image;
and 3, fitting the reconstructed multi-b-value diffusion weighted image of the lung based on the lung airway microstructure model to obtain lung microstructure parameters.
The acceleration factors corresponding to the different b values and the different sampling matrixes in the step 1 are obtained through the following steps:
step 1.1, performing single breath-hold hyperpolarized gas magnetic resonance multi-b value diffusion weighted imaging in a subject capable of holding breath for a long time to obtain full-sampling magnetic resonance images corresponding to all b values;
step 1.2, applying different sampling rates and sampling matrixes to the fully-sampled magnetic resonance image corresponding to a single b value to carry out undersampled retrospective reconstruction, and obtaining undersampled reconstructed images under different sampling rates corresponding to the b value;
step 1.3, calculating the average absolute error between undersampled reconstructed images under the respective sampling rates corresponding to the same b value and fully sampled magnetic resonance images corresponding to the same b value, selecting the reciprocal of the sampling rate corresponding to one of the average absolute errors which is smaller than or equal to an error threshold as a preliminary screening acceleration factor corresponding to the b value, and acquiring a corresponding sampling matrix as a preliminary screening sampling matrix corresponding to the b value;
step 1.4, repeating the steps 1.2 and 1.3 to obtain a primary screening acceleration factor and a primary screening sampling matrix corresponding to each b value;
step 1.5, replacing the subjects, repeating the steps 1.2, 1.3 and 1.4 to obtain the preliminary screening acceleration factors and preliminary screening sampling matrixes corresponding to the b values of different subjects, selecting the preliminary screening acceleration factor with the highest repetition rate in the preliminary screening acceleration factors corresponding to the b values as an optimal acceleration factor, wherein the preliminary screening sampling matrix corresponding to the optimal acceleration factor is an optimal sampling matrix, and the optimal acceleration factor and the optimal sampling matrix are respectively used as the acceleration factor and the sampling matrix corresponding to the b values in the step 1.
The error threshold as described above ranges from (0, ++ infinity A kind of electronic device.
The subject as described above is a human or an experimental animal, the experimental animal being a mouse or a rabbit or a dog or a pig; the hyperpolarized gas is 129 Xe or 3 He or He 83 Kr。
Compared with the prior art, the invention has the following advantages:
1. the method realizes the variable sampling rate DWI by adopting different acceleration factors through different b values for the first time, and the variable acceleration factors are adopted in the b value direction, so that the corresponding K space sampling matrixes are different. The scanning time is shortened, and the image quality is ensured;
2. the method is simple to operate and high in compatibility, and can be combined with the existing acceleration methods such as compressed sensing, deep learning, parallel imaging and the like, so that the scanning time is shortened;
3. according to the method, physiological parameters representing lung structures can be obtained by processing diffusion weighted image data acquired by changing sampling rates under different b values, and further the microstructure of the alveoli is quantitatively evaluated.
Drawings
FIG. 1 is a flow chart of the present invention.
Fig. 2 is a schematic diagram of a diffusion weighted imaging pulse sequence in an example.
Fig. 3 is a sampling matrix corresponding to different b values in the example.
Fig. 4 is a reconstructed multi-b-value diffusion weighted image of the lungs of a healthy subject in an example.
Detailed Description
According to the technical scheme of the invention, the technical scheme and the specific implementation of the invention are further described in detail below by taking the hyperpolarized xenon gas lung multi-b value variable sampling rate DWI of a subject under the imaging instrument of figures 1-4 and 3T as a specific example:
the hyperpolarized gas lung variable sampling rate rapid magnetic resonance diffusion weighted imaging method comprises the following steps:
step 1, sucking hyperpolarized gas into a subject, wherein the subject is human or experimental animal, and the experimental animal comprises mice, rabbits, dogs, pigs and the like, and the hyperpolarized gas can be 129 Xe or 3 He or He 83 Kr, the hyperpolarized gas is hyperpolarized xenon gas in this embodiment, then imaging scanning is performed in a single breath hold, and variable acceleration factor sampling is performed according to different acceleration factors and different sampling matrixes corresponding to different b-value (diffusion sensitivity factor) settings, so as to obtain lung multi-b-value weighted imaging data with variable sampling rate, wherein b-value in this embodiment comprises 0, 10, 20, 30s/cm 2 4 layers of images;
the diffusion weighted imaging pulse sequence may be 2D DWI or 3D DWI, and in this embodiment, as shown in fig. 2, a diffusion sensitive gradient is disposed inside a dashed frame and applied in a layer selection direction; the application direction of the diffusion sensitive gradient can be a layer selection direction or a phase direction or a reading direction, 2 diffusion sensitive gradients with the same size and opposite signs are applied, the diffusion sensitive gradient is G, the duration of the diffusion sensitive gradient is delta, and b is a diffusion sensitive factor. Diffusion weighted imaging at different b values is obtained by applying diffusion sensitive gradients of different magnitudes. b may be any value greater than 0.
The sampling matrixes corresponding to the different b values are different as shown in fig. 3;
step 2, reconstructing the lung multi-b-value weighted imaging data with the variable sampling rate obtained in the step 1 to obtain a lung reconstructed multi-b-value diffusion weighted image equivalent to full sampling; reconstruction can be realized in a manner of combining compressed sensing or deep learning and the like.
And 3, fitting the reconstructed multi-b-value diffusion weighted image of the lung based on the lung airway microstructure model to obtain lung microstructure parameters. The pulmonary airway microstructure model may be a cylindrical model or a tensile index model or a single chamber model.
A reconstructed multi-b-value diffusion weighted image of the lungs of the subject obtained using the method of this example is shown in fig. 4.
The acceleration factors corresponding to the different b values and the different sampling matrixes in the step 1 are obtained through the following steps:
step 1.1, performing single breath-hold hyperpolarized gas magnetic resonance multi-b-value diffusion weighted imaging in a subject capable of holding breath for a long time to obtain full-sampling magnetic resonance images corresponding to all b values, wherein the full-sampling magnetic resonance images corresponding to all b values form a full-sampling multi-b-value magnetic resonance image;
step 1.2, applying a series of different sampling rates and sampling matrixes to the fully-sampled magnetic resonance image corresponding to a single b value to carry out undersampled retrospective reconstruction, and obtaining an undersampled reconstructed image under a series of different sampling rates corresponding to the b value;
the specific operation is as follows: reconstructing a full-sampling magnetic resonance image corresponding to the same b value at multiple sampling rates, wherein the sampling rate range is [0.125,0.5], the interval is 0.025, and a series of undersampled reconstructed images corresponding to the same b value at different sampling rates are obtained;
step 1.3, comparing the undersampled reconstructed image under different sampling rates corresponding to the same b value obtained in step 1.2 with the full-sampled magnetic resonance image corresponding to the same b value obtained in step 1.1, respectively calculating average absolute errors between the undersampled reconstructed image under each sampling rate corresponding to the same b value and the full-sampled magnetic resonance image corresponding to the same b value (mean absolute error, MAE), a certain set value is taken as an error threshold, the range of the error threshold is (0, + -infinity), in the embodiment, 0.03 is taken as the error threshold, the reciprocal of the sampling rate corresponding to one of the average absolute errors MAE is smaller than or equal to the error threshold is selected as a primary screening acceleration factor corresponding to the b value, and a corresponding sampling matrix is obtained as a primary screening sampling matrix corresponding to the b value;
step 1.4, repeating the steps 1.2 and 1.3 to obtain a primary screening acceleration factor and a primary screening sampling matrix corresponding to each b value;
step 1.5, replacing the subjects, repeating the steps 1.2, 1.3 and 1.4 to obtain a preliminary screening acceleration factor and a preliminary screening sampling matrix corresponding to each b value of different subjects, selecting the preliminary screening acceleration factor with the highest repetition rate in each preliminary screening acceleration factor corresponding to the b value as an optimal acceleration factor, wherein the preliminary screening sampling matrix corresponding to the optimal acceleration factor is an optimal sampling matrix, the acceleration factors corresponding to the 4 b values are 8, 3 and 2, and the corresponding sampling matrix is shown in figure 3. And the optimal acceleration factor and the optimal sampling matrix are respectively used as the acceleration factor and the sampling matrix corresponding to the b value in the step 1.
The foregoing is a part of the detailed description of the present invention, and is merely illustrative of the method of the present invention, and various modifications and additions may be made to the described detailed description by those skilled in the art, which are not intended to limit the invention, but any modifications, equivalents, improvements or modifications etc. that fall within the spirit and principles of the present invention are intended to be included within the scope of the present invention.
Claims (3)
1. The hyperpolarized gas lung variable sampling rate rapid magnetic resonance diffusion weighted imaging method is characterized by comprising the following steps of:
step 1, a subject inhales hyperpolarized gas, then imaging scanning is carried out in a single breath-hold, and variable acceleration factor sampling is carried out according to different acceleration factors and different sampling matrixes corresponding to different b-value setting, so that lung multi-b-value weighted imaging data with variable sampling rate are obtained;
step 2, reconstructing the lung multi-b-value weighted imaging data with the variable sampling rate obtained in the step 1 to obtain a lung reconstructed multi-b-value diffusion weighted image;
step 3, fitting the reconstructed multi-b-value diffusion weighted image of the lung based on the lung airway microstructure model to obtain lung microstructure parameters,
the acceleration factors corresponding to the different b values and the different sampling matrixes in the step 1 are obtained through the following steps:
step 1.1, performing single breath-hold hyperpolarized gas magnetic resonance multi-b value diffusion weighted imaging in a subject capable of holding breath for a long time to obtain full-sampling magnetic resonance images corresponding to all b values;
step 1.2, applying different sampling rates and sampling matrixes to the fully-sampled magnetic resonance image corresponding to a single b value to carry out undersampled retrospective reconstruction, and obtaining undersampled reconstructed images under different sampling rates corresponding to the b value;
step 1.3, calculating the average absolute error between undersampled reconstructed images under the respective sampling rates corresponding to the same b value and fully sampled magnetic resonance images corresponding to the same b value, selecting the reciprocal of the sampling rate corresponding to one of the average absolute errors which is smaller than or equal to an error threshold as a preliminary screening acceleration factor corresponding to the b value, and acquiring a corresponding sampling matrix as a preliminary screening sampling matrix corresponding to the b value;
step 1.4, repeating the steps 1.2 and 1.3 to obtain a primary screening acceleration factor and a primary screening sampling matrix corresponding to each b value;
step 1.5, replacing the subjects, repeating the steps 1.2, 1.3 and 1.4 to obtain the preliminary screening acceleration factors and preliminary screening sampling matrixes corresponding to the b values of different subjects, selecting the preliminary screening acceleration factor with the highest repetition rate in the preliminary screening acceleration factors corresponding to the b values as an optimal acceleration factor, wherein the preliminary screening sampling matrix corresponding to the optimal acceleration factor is an optimal sampling matrix, and the optimal acceleration factor and the optimal sampling matrix are respectively used as the acceleration factor and the sampling matrix corresponding to the b values in the step 1.
2. The hyperpolarized gas pulmonary variable sampling rate fast magnetic resonance diffusion weighted imaging method of claim 1, wherein the error threshold is in the range of (0, ++ -infinity).
3. The hyperpolarized gas pulmonary variable sampling rate rapid magnetic resonance diffusion weighted imaging method of claim 1, wherein the subject is a human or laboratory animal, and the laboratory animal is a mouse or rabbit or dog or pig; said superPolarized gas is 129 Xe or 3 He or He 83 Kr。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111466215.9A CN114236444B (en) | 2021-12-03 | 2021-12-03 | Hyperpolarized gas lung variable sampling rate rapid magnetic resonance diffusion weighted imaging method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111466215.9A CN114236444B (en) | 2021-12-03 | 2021-12-03 | Hyperpolarized gas lung variable sampling rate rapid magnetic resonance diffusion weighted imaging method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114236444A CN114236444A (en) | 2022-03-25 |
CN114236444B true CN114236444B (en) | 2023-06-30 |
Family
ID=80752874
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111466215.9A Active CN114236444B (en) | 2021-12-03 | 2021-12-03 | Hyperpolarized gas lung variable sampling rate rapid magnetic resonance diffusion weighted imaging method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114236444B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117192456A (en) * | 2023-08-16 | 2023-12-08 | 中南大学湘雅三医院 | Magnetic resonance model for detecting fat content, construction method, verification method and application thereof |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106249183A (en) * | 2016-09-24 | 2016-12-21 | 中国科学院武汉物理与数学研究所 | A kind of hyperpolarization xenon magnetic resonance method based on spectrum picture integration |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7885702B2 (en) * | 2006-04-19 | 2011-02-08 | Wisconsin Alumni Research Foundation | Segmentation of the airway tree using hyperpolarized noble gases and diffusion weighted magnetic resonance imaging |
CN101596109B (en) * | 2009-06-12 | 2012-01-25 | 深圳先进技术研究院 | Method and system for acquiring brain characteristic parameters and system for generating thrombolytic indication |
CN104799859B (en) * | 2014-01-27 | 2019-01-08 | 西门子(深圳)磁共振有限公司 | A kind of bearing calibration of Diffusion-weighted imaging image and device |
CN106355624B (en) * | 2016-08-26 | 2018-12-25 | 中国科学院武汉物理与数学研究所 | A kind of lung's hyperpolarized gas dynamic imaging methods based on variable sampling rate |
CN109256023B (en) * | 2018-11-28 | 2020-11-24 | 中国科学院武汉物理与数学研究所 | Measuring method of lung airway microstructure model |
CN110558985A (en) * | 2019-08-27 | 2019-12-13 | 中国科学院武汉物理与数学研究所 | rapid functional magnetic resonance imaging method for evaluating PM 2.5-induced lung injury |
CN110728624B (en) * | 2019-09-29 | 2021-07-23 | 厦门大学 | High-resolution diffusion weighted image reconstruction method |
-
2021
- 2021-12-03 CN CN202111466215.9A patent/CN114236444B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106249183A (en) * | 2016-09-24 | 2016-12-21 | 中国科学院武汉物理与数学研究所 | A kind of hyperpolarization xenon magnetic resonance method based on spectrum picture integration |
Also Published As
Publication number | Publication date |
---|---|
CN114236444A (en) | 2022-03-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Sandino et al. | Compressed sensing: From research to clinical practice with deep neural networks: Shortening scan times for magnetic resonance imaging | |
JP6557710B2 (en) | Nuclear magnetic resonance (NMR) fingerprinting | |
Hollingsworth | Reducing acquisition time in clinical MRI by data undersampling and compressed sensing reconstruction | |
CN108335339B (en) | Magnetic resonance reconstruction method based on deep learning and convex set projection | |
Adluru et al. | Acquisition and reconstruction of undersampled radial data for myocardial perfusion magnetic resonance imaging | |
CN103800006B (en) | Motional error correction in functional magnetic resonance imaging | |
US20160148378A1 (en) | Systems and Methods for Three-Dimensional Spiral Perfusion Imaging | |
US11170543B2 (en) | MRI image reconstruction from undersampled data using adversarially trained generative neural network | |
Cole et al. | Analysis of deep complex-valued convolutional neural networks for MRI reconstruction | |
CN116774121A (en) | Magnetic resonance imaging system and method | |
Rathi et al. | Diffusion propagator estimation from sparse measurements in a tractography framework | |
CN108294753A (en) | The acquisition methods and device of magnetic resonance quantitative information figure | |
CN113470139A (en) | CT image reconstruction method based on MRI | |
CN114236444B (en) | Hyperpolarized gas lung variable sampling rate rapid magnetic resonance diffusion weighted imaging method | |
Eirich et al. | Cardiac real‐time MRI using a pre‐emphasized spiral acquisition based on the gradient system transfer function | |
CN114599985A (en) | Deep learning system and method for large-scale dynamic magnetic resonance image reconstruction | |
Kleineisel et al. | Real‐time cardiac MRI using an undersampled spiral k‐space trajectory and a reconstruction based on a variational network | |
CN111012349A (en) | System and method for signal characterization determination in magnetic resonance imaging | |
Chen et al. | Compressed sensing in sodium magnetic resonance imaging: techniques, applications, and future prospects | |
WO2024093083A1 (en) | Magnetic resonance weighted image synthesis method and apparatus based on variational autoencoder | |
Yu et al. | Universal generative modeling in dual domains for dynamic MRI | |
Huang et al. | Optimization of PROPELLER reconstruction for free‐breathing T1‐weighted cardiac imaging | |
CN113192150B (en) | Magnetic resonance interventional image reconstruction method based on cyclic neural network | |
Liu et al. | A three‐dimensional Magnetic Resonance Spin Tomography in Time‐domain protocol for high‐resolution multiparametric quantitative magnetic resonance imaging | |
CN113341357B (en) | vBM3 d-based magnetic resonance image reconstruction method |
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 |