CN110568391B - Magnetic resonance imaging method, system and related device - Google Patents
Magnetic resonance imaging method, system and related device Download PDFInfo
- Publication number
- CN110568391B CN110568391B CN201910854833.7A CN201910854833A CN110568391B CN 110568391 B CN110568391 B CN 110568391B CN 201910854833 A CN201910854833 A CN 201910854833A CN 110568391 B CN110568391 B CN 110568391B
- Authority
- CN
- China
- Prior art keywords
- dimensional
- frequency information
- image
- magnetic resonance
- resonance 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
-
- 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
- G01R33/4818—MR characterised by data acquisition along a specific k-space trajectory or by the temporal order of k-space coverage, e.g. centric or segmented coverage of k-space
Landscapes
- Physics & Mathematics (AREA)
- High Energy & Nuclear Physics (AREA)
- Condensed Matter Physics & Semiconductors (AREA)
- General Physics & Mathematics (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The present application provides a magnetic resonance imaging method comprising: acquiring a two-dimensional airspace image; superposing the two-dimensional airspace images to obtain a three-dimensional airspace image; performing feature extraction on the three-dimensional airspace image by using a three-dimensional tight frame to obtain low-frequency information and high-frequency information; constructing a sparsity model according to the low-frequency information, the high-frequency information and the sparsity constraint; a magnetic resonance image is generated using the sparsity model. Two-dimensional images are stacked together to form three-dimensional image data, a three-dimensional tight frame is used for carrying out feature extraction and constraint on the three-dimensional images, and sparsity constraint is carried out on three-dimensional high-frequency information in feature information of the three-dimensional tight frame, so that aliasing artifacts of reconstructed images are less, and the quality of the reconstructed images is improved. The present application further provides a magnetic resonance imaging system, a computer readable storage medium and a magnetic resonance imaging apparatus having the above-mentioned advantageous effects.
Description
Technical Field
The present application relates to the field of image processing, and in particular, to a magnetic resonance imaging method, system and related apparatus.
Background
The parallel Magnetic Resonance imaging (pMRI) is an imaging technology based on the nuclear Magnetic Resonance phenomenon, is different from imaging technologies such as CT, X-ray and the like, uses a Magnetic field atomic Resonance effect in the pMRI, has no ionizing radiation damage to a human body, obtains a large amount of information, can obtain primary three-dimensional section imaging, and has clear display on a soft tissue structure and high resolution.
Limited by the nyquist sampling theorem, pMRI devices have long scan times, suffer from patient discomfort due to excessively fast gradient magnetic field switching frequencies, use of dense radio frequency pulses for short periods, and internal body tissue heating due to the accumulation of radio frequency energy. The way to increase the sampling speed by hardware has basically reached a bottleneck.
To accelerate the scan rate, k-space is down-sampled to obtain partially acquired coil images. The non-acquired information portions are recovered from the correlation between the coils or their spatial sensitivity. When the sampling rate is low, the scanned image has serious aliasing artifacts and noises, which affect the imaging quality, and more accurate non-sampled information needs to be reconstructed by technical means, so that the quality of the reconstructed image is improved.
Parallel magnetic resonance imaging reconstruction techniques generally improve the quality of a reconstructed image by using regularization constraints, such as total variation regularization, sparse representation techniques of wavelet transform, and the like, all aim at a single coil two-dimensional image, and do not consider the inherent correlation between coil images. When the sampling rate is low, the scan reconstruction image has serious aliasing artifacts and amplification system noise, which affects the imaging quality.
Disclosure of Invention
An object of the present application is to provide a magnetic resonance imaging method, system, computer-readable storage medium and a magnetic resonance imaging apparatus, which can reduce aliasing artifacts of a magnetic resonance image and improve image quality.
In order to solve the technical problem, the present application provides a magnetic resonance imaging method, which has the following specific technical scheme:
acquiring a two-dimensional airspace image;
superposing the two-dimensional airspace images to obtain a three-dimensional airspace image;
performing feature extraction on the three-dimensional airspace image by using a three-dimensional tight frame to obtain low-frequency information and high-frequency information:
constructing a sparsity model according to the low-frequency information, the high-frequency information and sparsity constraint;
generating a magnetic resonance image using the sparsity model.
Before acquiring the two-dimensional airspace image, the method further comprises the following steps:
acquiring an undersampled signal of a part to be detected by using a nuclear magnetic resonance machine;
and obtaining the two-dimensional space domain image according to the undersampled signals and a parallel magnetic resonance imaging algorithm.
The method comprises the following steps of utilizing a three-dimensional tight frame to carry out feature extraction on the three-dimensional airspace image, and obtaining low-frequency information and high-frequency information, wherein the method comprises the following steps:
performing layered feature extraction on every 8 data points in the three-dimensional airspace image by using a three-dimensional tight frame to obtain 1 piece of low-frequency information and 13 pieces of high-frequency information;
the 8 data points are 8 vertexes of a cuboid, the upper surface and the lower surface of the cuboid belong to different two-dimensional airspace images respectively, and the height of the cuboid is the stacking direction of the two-dimensional airspace images; when the n-th layer of multi-resolution feature extraction is carried out, the interval between the adjacent data points is 2n-1-1 pixel; after n layers of feature extraction, 1 piece of low-frequency information and 13n pieces of high-frequency information are obtained.
The present application further provides a magnetic resonance imaging system comprising:
the acquisition module is used for acquiring a two-dimensional airspace image;
the superposition module is used for superposing the two-dimensional airspace images to obtain three-dimensional airspace images;
the characteristic extraction module is used for extracting the characteristics of the three-dimensional airspace image by utilizing a three-dimensional tight frame to obtain low-frequency information and high-frequency information;
the model construction module is used for constructing a sparsity model according to the low-frequency information, the high-frequency information and the sparsity constraint;
and the image generation module is used for generating a magnetic resonance image by utilizing the sparsity model.
Wherein, still include:
the detection module is used for acquiring an undersampled signal of the part to be detected by using a nuclear magnetic resonance machine;
and the two-dimensional image generation module is used for obtaining the two-dimensional airspace image according to the undersampled signals and a parallel magnetic resonance imaging algorithm.
Wherein the feature extraction module comprises:
the hierarchical extraction unit is used for extracting hierarchical characteristics of every 8 data points in the three-dimensional airspace image by using a three-dimensional tight frame to obtain 1 piece of low-frequency information and 13 pieces of high-frequency information;
the 8 data points are 8 vertexes of a cuboid, the upper surface and the lower surface of the cuboid belong to different two-dimensional airspace images respectively, and the height of the cuboid is the stacking direction of the two-dimensional airspace images; when the n-th layer of multi-resolution feature extraction is carried out, the interval between the adjacent data points is 2n-1-1 pixel; after n layers of feature extraction, 1 piece of low-frequency information and 13n pieces of high-frequency information are obtained.
The present application further provides a computer-readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the magnetic resonance imaging method as set forth above.
The present application further provides a magnetic resonance imaging apparatus comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the magnetic resonance imaging method as described above when calling the computer program in the memory.
The present application provides a magnetic resonance imaging method comprising: acquiring a two-dimensional airspace image; superposing the two-dimensional airspace images to obtain a three-dimensional airspace image; performing feature extraction on the three-dimensional airspace image by using a three-dimensional tight frame to obtain low-frequency information and high-frequency information; constructing a sparsity model according to the low-frequency information, the high-frequency information and sparsity constraint; generating a magnetic resonance image using the sparsity model.
According to the method, two-dimensional images are stacked together to form three-dimensional image data, and the three-dimensional images are subjected to feature extraction and constraint by using a new three-dimensional tight frame, so that multi-resolution three-dimensional tight frame feature information is obtained. By means of the obtained multi-resolution three-dimensional tight frame characteristic information and sparsity constraint, a three-dimensional airspace image can be completely reconstructed, aliasing artifacts of the reconstructed image are less, and the quality of the reconstructed image is improved. The present application further provides a magnetic resonance imaging system, a computer-readable storage medium, and a magnetic resonance imaging apparatus, which have the above-mentioned advantages and are not described herein again.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a magnetic resonance imaging method according to an embodiment of the present application;
fig. 2 is a schematic diagram of positions of sampling data points in a process of extracting layers of a three-dimensional spatial domain image according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of a three-dimensional spatial domain image according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of a magnetic resonance imaging system according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, fig. 1 is a flowchart of a magnetic resonance imaging method according to an embodiment of the present application, the method including:
s101: acquiring a two-dimensional airspace image;
in this step, a two-dimensional airspace image needs to be acquired, and the generation and acquisition processes of the two-dimensional airspace image are not specifically limited. An under-sampled signal of a part to be detected can be obtained by using a nuclear magnetic resonance machine, and then a two-dimensional airspace image is obtained according to the under-sampled signal and a parallel magnetic resonance imaging algorithm.
S102: superposing the two-dimensional airspace images to obtain a three-dimensional airspace image;
in this step, the two-dimensional airspace images obtained in S101 need to be superimposed to obtain a three-dimensional airspace image. Specifically, the two-dimensional airspace image is superposed, and the three-dimensional airspace image can be obtained without other data processing. In addition, since the two-dimensional spatial domain images are superimposed to obtain a three-dimensional spatial domain image for facilitating feature extraction in the subsequent step, the interval length between adjacent two-dimensional spatial domain images is not particularly limited or required, but is usually an integer multiple of a unit pixel.
S103: performing feature extraction on the three-dimensional airspace image by using a three-dimensional tight frame to obtain low-frequency information and high-frequency information;
the method comprises the following steps of extracting the characteristics of a three-dimensional airspace image, extracting the multi-resolution image characteristic information of an obtained three-dimensional tight frame, namely high-frequency information and low-frequency information, by utilizing the internal relation among a plurality of coil image data, and further processing the multi-resolution image characteristic information, so that the three-dimensional image data which reduces artifacts and keeps edge details can be reconstructed, wherein the specific process can be as follows:
carrying out layered feature extraction on every 8 data points in the three-dimensional airspace image by using a three-dimensional tight frame to obtain low-frequency information and thirteen high-frequency information;
the system comprises 8 data points, a plurality of spatial domain images and a plurality of spatial domain images, wherein the 8 data points are 8 vertexes of a cuboid, the upper surface and the lower surface of the cuboid belong to different two-dimensional spatial domain images respectively, and the height of the cuboid is the stacking direction of the two-dimensional spatial domain images; when the n-th layer of multi-resolution feature extraction is carried out, the interval between adjacent data points is 2n-1-1 pixel. After n layers of feature extraction, 1 piece of low-frequency information and 13n pieces of high-frequency information are obtained.
Referring to fig. 2, fig. 2 is a schematic diagram of positions of sampling data points in a process of extracting layers of a three-dimensional spatial domain image provided in the embodiment of the present application, and a schematic diagram of a three-dimensional coordinate system is given at the leftmost side. It is easy to see that, when the first layer of features is extracted, feature extraction is carried out on every 8 data points between adjacent coils to obtain three-dimensional low-frequency information and thirteen three-dimensional high-frequency information. In order to make the size of the obtained multi-resolution three-dimensional tight frame feature information the same as that of the original three-dimensional airspace image, zero padding is carried out or boundary data are copied when feature extraction is carried out on boundary points. The 8 data points are derived from four data points which correspond up and down in two adjacent two-dimensional space domain images, and a cuboid with the length and the width of 1 pixel is formed. It should be noted that, in practice, each two-dimensional spatial domain image has been superimposed in step S102, fig. 2 enlarges the interval between two adjacent two-dimensional spatial domain images for clearly illustrating the relationship between data points, and in practice, the interval between two-dimensional spatial domain images and the ratio of the two-dimensional spatial domain images to the unit pixel are not necessarily as shown in fig. 2. And when the second layer of features is extracted, selecting the three-dimensional low-frequency information obtained by extracting the first layer of features, and extracting the features of every 8 data points to obtain one piece of three-dimensional low-frequency information and thirteen pieces of three-dimensional high-frequency information. These 8 data points originate from intervalsFour data points which correspond to each other up and down in two-dimensional space domain images of one two-dimensional space domain image form a cuboid with the length and the width of 1 pixel. The vertices of the cuboid, i.e. the data points, are spaced 1 pixel apart. And when the characteristics of the nth layer are extracted, selecting the three-dimensional low-frequency information obtained by the characteristics extraction of the (n-1) th layer, and extracting the characteristics of every 8 data points of the three-dimensional low-frequency information to obtain three-dimensional low-frequency information and thirteen three-dimensional high-frequency information. These 8 data points originate from interval 2n-1Four data points corresponding to each upper and lower position in two-dimensional space domain images of the 1 two-dimensional space domain image form a cuboid with the length and the width of 1 pixel. The vertices of the cuboid, i.e. the intervals 2 between the data pointsn-1-1 pixel. And finally, three-dimensional low-frequency information and 13n three-dimensional high-frequency information can be obtained.
Further, referring to fig. 3, the dashed-dotted lines in fig. 3 respectively connect two data points, which represent high-frequency filters in different directions, so that 13 pieces of high-frequency information can be obtained, wherein, the x, y and z directions respectively have a high frequency information, the xy, xz and yz directions respectively have two high frequency information, the xyz direction has four high frequency information, the arithmetic mean of the 8 points is taken as the low frequency information, namely, the high frequency information in the x direction is (a2-a4)/8, the high frequency information in the y direction is (a3-a4)/8, the high frequency information in the z direction is (b4-a4)/8, the high frequency information in the xy direction is (a1-a4)/8 and (a2-a3)/8, and so on, high-frequency information in xz, yz and xyz directions can be obtained, and the low-frequency information is (a1+ a2+ a3+ a4+ b1+ b2+ b3+ b 4)/8. And the three-dimensional space domain image can be completely reconstructed through the obtained multi-resolution three-dimensional tight frame characteristic information.
In fact, the purpose of this step is to utilize the internal relationship between the image data of multiple coils to obtain the three-dimensional MRI image characteristic information with different resolutions,
s104: constructing a sparsity model according to the low-frequency information, the high-frequency information and the sparsity constraint;
after the low-frequency information and the high-frequency information are determined, a sparsity model can be constructed by combining sparsity constraint. The sparsity constraint is not particularly limited, and may be, for example, an L1 norm constraint.
S105: a magnetic resonance image is generated using the sparsity model.
According to the method, two-dimensional images are stacked together to form three-dimensional image data, and the three-dimensional images are subjected to feature extraction and constraint by using a new three-dimensional tight frame, so that multi-resolution three-dimensional tight frame feature information is obtained. By means of the obtained multi-resolution three-dimensional tight frame characteristic information and sparsity constraint, a three-dimensional airspace image can be completely reconstructed, aliasing artifacts of the reconstructed image are less, and the quality of the reconstructed image is improved.
In the following, a magnetic resonance imaging system provided by an embodiment of the present application is described, and a magnetic resonance imaging system described below and a magnetic resonance imaging method described above are referred to in correspondence.
Referring to fig. 4, fig. 4 is a schematic structural diagram of a magnetic resonance imaging system according to an embodiment of the present application, where the system includes:
an obtaining module 100, configured to obtain a two-dimensional spatial domain image;
the superposition module 200 is used for superposing the two-dimensional airspace images to obtain three-dimensional airspace images;
the feature extraction module 300 is configured to perform feature extraction on the three-dimensional airspace image by using a three-dimensional tight frame to obtain low-frequency information and high-frequency information;
a model construction module 400, configured to construct a sparsity model according to the low-frequency information, the high-frequency information, and a sparsity constraint;
an image generation module 500 for generating a magnetic resonance image using the sparsity model.
Based on the above embodiment, as a preferred embodiment, the method further includes:
the detection module is used for acquiring an undersampled signal of the part to be detected by using a nuclear magnetic resonance machine;
and the two-dimensional image generation module is used for obtaining the two-dimensional airspace image according to the undersampled signals and a parallel magnetic resonance imaging algorithm.
Based on the above embodiment, as a preferred embodiment, the feature extraction module 300 includes, in a spatial domain:
the hierarchical extraction unit is used for extracting hierarchical characteristics of every 8 data points in the three-dimensional airspace image by using a three-dimensional tight frame to obtain 1 piece of low-frequency information and 13 pieces of high-frequency information;
the 8 data points are 8 vertexes of a cuboid, the upper surface and the lower surface of the cuboid belong to different two-dimensional airspace images respectively, and the height of the cuboid is the stacking direction of the two-dimensional airspace images; and when the nth layer of multi-resolution feature extraction is carried out, the interval between the adjacent data points is one pixel. After n layers of features are extracted, 1 piece of low-frequency information and 13n pieces of high-frequency information are obtained.
The present application also provides a computer readable storage medium having stored thereon a computer program which, when executed, may implement the steps provided by the above-described embodiments. The storage medium may include: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The present application further provides a magnetic resonance imaging apparatus, which may include a memory and a processor, where the memory stores a computer program, and the processor may implement the steps provided in the foregoing embodiments when calling the computer program in the memory. Of course, the magnetic resonance imaging apparatus may further include various network interfaces, power supplies, and the like.
The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system provided by the embodiment, the description is relatively simple because the system corresponds to the method provided by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present application are explained herein using specific examples, which are provided only to help understand the method and the core idea of the present application. It should be noted that, for those skilled in the art, it is possible to make several improvements and modifications to the present application without departing from the principle of the present application, and such improvements and modifications also fall within the scope of the claims of the present application.
It is further noted that, in the present specification, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Claims (6)
1. A magnetic resonance imaging method, comprising:
acquiring a two-dimensional airspace image;
superposing the two-dimensional airspace images to obtain a three-dimensional airspace image;
performing feature extraction on the three-dimensional airspace image by using a three-dimensional tight frame to obtain low-frequency information and high-frequency information;
constructing a sparsity model according to the low-frequency information, the high-frequency information and sparsity constraint;
generating a magnetic resonance image using the sparsity model;
the method comprises the following steps of utilizing a three-dimensional tight frame to carry out feature extraction on the three-dimensional airspace image, and obtaining low-frequency information and high-frequency information, wherein the method comprises the following steps:
performing layered feature extraction on every 8 data points in the three-dimensional airspace image by using a three-dimensional tight frame to obtain 1 piece of low-frequency information and 13 pieces of high-frequency information; the system comprises a power supply, a power supply and a power supply, wherein;
the 8 data points are 8 vertexes of a cuboid, the upper surface and the lower surface of the cuboid belong to different two-dimensional airspace images respectively, and the height of the cuboid is the stacking direction of the two-dimensional airspace images; when the n-th layer of multi-resolution feature extraction is carried out, the interval between the adjacent data points is 2n-1-1 pixel; after n layers of feature extraction, 1 piece of low-frequency information and 13n pieces of high-frequency information are obtained.
2. The magnetic resonance imaging method according to claim 1, further comprising, before acquiring the two-dimensional spatial domain image:
acquiring an undersampled signal of a part to be detected by using a nuclear magnetic resonance machine;
and obtaining the two-dimensional space domain image according to the undersampled signals and a parallel magnetic resonance imaging algorithm.
3. A magnetic resonance imaging system, comprising:
the acquisition module is used for acquiring a two-dimensional airspace image;
the superposition module is used for superposing the two-dimensional airspace images to obtain three-dimensional airspace images;
the characteristic extraction module is used for extracting the characteristics of the three-dimensional airspace image by utilizing a three-dimensional tight frame to obtain low-frequency information and high-frequency information;
the model construction module is used for constructing a sparsity model according to the low-frequency information, the high-frequency information and the sparsity constraint;
an image generation module for generating a magnetic resonance image using the sparsity model;
the feature extraction module comprises a layered extraction unit and is used for extracting features of the three-dimensional airspace image by using a three-dimensional tight frame, and obtaining low-frequency information and high-frequency information comprises:
performing layered feature extraction on every 8 data points in the three-dimensional airspace image by using a three-dimensional tight frame to obtain 1 piece of low-frequency information and 13 pieces of high-frequency information; the system comprises a power supply, a power supply and a power supply, wherein;
the 8 data points are 8 vertexes of a cuboid, the upper surface and the lower surface of the cuboid belong to different two-dimensional airspace images respectively, and the height of the cuboid is the stacking direction of the two-dimensional airspace images; when the n-th layer of multi-resolution feature extraction is carried out, the interval between the adjacent data points is 2n-1-1 pixel; after n layers of feature extraction, 1 piece of low-frequency information and 13n pieces of high-frequency information are obtained.
4. The magnetic resonance imaging system of claim 3, further comprising:
the detection module is used for acquiring an undersampled signal of the part to be detected by using a nuclear magnetic resonance machine;
and the two-dimensional image generation module is used for obtaining the two-dimensional airspace image according to the undersampled signals and a parallel magnetic resonance imaging algorithm.
5. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the magnetic resonance imaging method as set forth in any one of claims 1-2.
6. A magnetic resonance imaging apparatus comprising a memory having a computer program stored therein and a processor implementing the steps of the magnetic resonance imaging method as claimed in any one of claims 1-2 when the processor invokes the computer program in the memory.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910854833.7A CN110568391B (en) | 2019-09-10 | 2019-09-10 | Magnetic resonance imaging method, system and related device |
PCT/CN2019/114663 WO2021046989A1 (en) | 2019-09-10 | 2019-10-31 | Magnetic resonance imaging method and system, and related apparatus |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910854833.7A CN110568391B (en) | 2019-09-10 | 2019-09-10 | Magnetic resonance imaging method, system and related device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110568391A CN110568391A (en) | 2019-12-13 |
CN110568391B true CN110568391B (en) | 2020-09-04 |
Family
ID=68778911
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910854833.7A Active CN110568391B (en) | 2019-09-10 | 2019-09-10 | Magnetic resonance imaging method, system and related device |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN110568391B (en) |
WO (1) | WO2021046989A1 (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112633298B (en) * | 2020-12-28 | 2023-07-18 | 深圳大学 | Method for measuring similarity of image/image block |
Family Cites Families (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7902823B2 (en) * | 2007-05-02 | 2011-03-08 | Griswold Mark A | Dynamic parallel magnetic resonance imaging(DpMRI) with sparse data |
CN101520499B (en) * | 2008-02-29 | 2011-12-07 | 西门子(中国)有限公司 | Method and device for removing artifacts in magnetic resonance imaging |
CN103443643B (en) * | 2010-09-01 | 2016-08-10 | 原子能与替代能源委员会 | For the method performing parallel MR imaging |
US9453895B2 (en) * | 2012-10-05 | 2016-09-27 | Siemens Aktiengesellschaft | Dynamic image reconstruction with tight frame learning |
CN102937706B (en) * | 2012-10-31 | 2016-08-03 | 中国科学院深圳先进技术研究院 | A kind of MRI parallel imaging method utilizing and magnetic resonance imager |
CN103632341A (en) * | 2013-08-30 | 2014-03-12 | 王勇 | Noisy CS-MRI reconstruction method for pyramid decomposition and dictionary learning |
CN104714199B (en) * | 2013-12-17 | 2018-04-24 | 西门子(深圳)磁共振有限公司 | A kind of MR imaging method and device |
CN105334479B (en) * | 2014-06-10 | 2019-02-22 | 西门子(深圳)磁共振有限公司 | A kind of MR imaging method and device |
CN107633496B (en) * | 2017-08-30 | 2020-04-07 | 北京航空航天大学 | Image fusion method guided by high-frequency information and based on sparse representation |
CN109959887A (en) * | 2017-12-26 | 2019-07-02 | 深圳先进技术研究院 | A kind of three-dimensional MRI method for reconstructing, device, application and readable medium |
CN109009109A (en) * | 2018-06-25 | 2018-12-18 | 深圳大学 | Method, apparatus, equipment and the storage medium of three-dimensional parallel MR imaging |
-
2019
- 2019-09-10 CN CN201910854833.7A patent/CN110568391B/en active Active
- 2019-10-31 WO PCT/CN2019/114663 patent/WO2021046989A1/en active Application Filing
Also Published As
Publication number | Publication date |
---|---|
CN110568391A (en) | 2019-12-13 |
WO2021046989A1 (en) | 2021-03-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111513716B (en) | Method and system for magnetic resonance image reconstruction using an extended sensitivity model and a deep neural network | |
US11300645B2 (en) | Deep learning techniques for magnetic resonance image reconstruction | |
US10489943B2 (en) | System and method for sparse image reconstruction | |
CN111081354B (en) | System and method for denoising medical images through deep learning network | |
Chen et al. | A novel method and fast algorithm for MR image reconstruction with significantly under-sampled data | |
EP3779866A1 (en) | Systems and methods for deblurring medical images using deep neural network | |
Liu et al. | SparseSENSE: application of compressed sensing in parallel MRI | |
CN104939828B (en) | MR imaging method | |
US20220130084A1 (en) | Systems and methods for medical image processing using deep neural network | |
Zhu et al. | Compressed Sensing‐Based MRI Reconstruction Using Complex Double‐Density Dual‐Tree DWT | |
US10101424B2 (en) | Robust principal component analysis for separation of on and off-resonance in 3D multispectral MRI | |
CN107205686B (en) | Method for removing ghost artifacts in magnetic resonance imaging and magnetic resonance device therefor | |
CN110568391B (en) | Magnetic resonance imaging method, system and related device | |
CN108324276A (en) | MR imaging method and device | |
Miao et al. | A simple application of compressed sensing to further accelerate partially parallel imaging | |
Robini et al. | A stochastic continuation approach to piecewise constant reconstruction | |
KR101580532B1 (en) | Apparatus and method for magnetic resonance image processing | |
US20180203085A1 (en) | Magnetic resonance imaging with undersampling | |
Shah et al. | Compressively sampled MR image reconstruction using hyperbolic tangent-based soft-thresholding | |
CN112557981B (en) | Improved algorithm of parallel magnetic resonance imaging | |
CN114723644A (en) | Compressed sensing magnetic resonance image reconstruction method and device, storage medium and electronic equipment | |
Zhu et al. | Compressed sensing mri by two-dimensional wavelet filter banks | |
Möller et al. | Blind sparse motion MRI with linear subpixel interpolation | |
WO2018037868A1 (en) | Magnetic resonance imaging device and image reconstruction method | |
CN115267898B (en) | Method and device for reconstructing natural seismic data and electronic equipment |
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 |