CN111044958A - Tissue classification method, device, storage medium and magnetic resonance imaging system - Google Patents
Tissue classification method, device, storage medium and magnetic resonance imaging system Download PDFInfo
- Publication number
- CN111044958A CN111044958A CN201911347737.XA CN201911347737A CN111044958A CN 111044958 A CN111044958 A CN 111044958A CN 201911347737 A CN201911347737 A CN 201911347737A CN 111044958 A CN111044958 A CN 111044958A
- Authority
- CN
- China
- Prior art keywords
- magnetic resonance
- image
- amplitude
- tissue
- image unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
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
- G01R33/28—Details of apparatus provided for in groups G01R33/44 - G01R33/64
- G01R33/32—Excitation or detection systems, e.g. using radio frequency signals
- G01R33/36—Electrical details, e.g. matching or coupling of the coil to the receiver
Landscapes
- Physics & Mathematics (AREA)
- Condensed Matter Physics & Semiconductors (AREA)
- General Physics & Mathematics (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The application discloses a tissue classification method and device of a magnetic resonance image, a storage medium and a magnetic resonance imaging system. The tissue classification method of the magnetic resonance image comprises the following steps: applying presaturation pulses with different preset frequency values for multiple times in an imaging visual field, acquiring magnetic resonance data under the condition that the presaturation pulses with the preset frequency values are applied every time, and reconstructing according to the magnetic resonance data to obtain a plurality of magnetic resonance amplitude images; determining a change curve of the amplitude value of the image unit at the same position in the plurality of magnetic resonance amplitude images and a preset frequency value according to the plurality of reconstructed magnetic resonance amplitude images; and classifying the tissue types corresponding to the image units according to the change curves. By the method and the device, the problem that the requirement of the tissue classification method on the main magnetic field uniformity in the related technology is high is solved, and the requirement of the tissue classification method on the main magnetic field uniformity is reduced.
Description
Technical Field
The present application relates to the field of magnetic resonance imaging, and in particular, to a method and an apparatus for tissue classification of a magnetic resonance image, a storage medium, and a magnetic resonance imaging system.
Background
Magnetic resonance imaging has long been used clinically very widely as a non-invasive early diagnostic modality. In the magnetic resonance image obtained by the magnetic resonance imaging, the strong signal of fat often interferes with the diagnosis and application in treatment of the lesion, and the contrast of the lesion needs to be increased by inhibiting the signal of fat, namely, the magnetic resonance image is subjected to tissue classification. Commonly used tissue classification methods generally use water-fat separation techniques.
The basic principle of the water-fat separation technology is that Larmor frequency difference of water protons and fat protons is utilized, two times of acquisition are carried out by adjusting echo Time (TE), the transverse magnetization vectors of the two components are in the same phase by the first acquisition, and the sum image of water and fat is obtained; the second acquisition reverses their phase to obtain a difference image. And performing addition and subtraction operation on the sum image and the difference image to separate a water image and a fat image. However, the water-fat separation technology fails under the condition of uneven main magnetic field, and water and fat components cannot be separated correctly; the echo Time (TE) needs to be adjusted for two acquisitions, resulting in a long time for tissue classification; and related art tissue classification methods generally classify only water and fat tissues, making it difficult to further distinguish tissue types, such as muscle, lung tissue, brain tissue, and the like.
Disclosure of Invention
The embodiment of the application provides a tissue classification method, a tissue classification device, a storage medium and a magnetic resonance imaging system of a magnetic resonance image, so as to at least solve the problem that the requirement of the tissue classification method in the related art on main magnetic field uniformity is high.
In a first aspect, an embodiment of the present application provides a method for classifying tissues in a magnetic resonance image, including: applying presaturation pulses with different preset frequency values for multiple times in an imaging visual field, acquiring magnetic resonance data under the condition that the presaturation pulses with the preset frequency values are applied every time, and reconstructing according to the magnetic resonance data to obtain a plurality of magnetic resonance amplitude images; determining a change curve of the amplitude of the image unit at the same position in the plurality of magnetic resonance amplitude images and the preset frequency value according to the plurality of reconstructed magnetic resonance amplitude images; and classifying the tissue types corresponding to the image units according to the change curves.
In one embodiment, the pre-saturation pulse comprises one or more radio frequency pulses with frequency selectivity; the plurality of preset frequency values comprises: a resonant frequency value and a partial resonant frequency value in a preset range at both sides of the resonant frequency value.
In one embodiment, classifying the tissue type corresponding to the image unit according to the variation curve includes: fitting a signal peak in the variation curve using a preset function, the signal peak comprising: a water peak and/or a fat peak; classifying the tissue type corresponding to the image unit according to the characteristics of the signal peak, wherein the characteristics of the signal peak comprise: the amplitude and/or full width at half maximum of the signal peak.
In one embodiment, classifying the tissue type corresponding to the image unit according to the feature of the signal peak comprises: inputting the characteristics of the signal peak into a machine learning model with complete training to obtain a classification result, wherein the classification result is used for representing the tissue type corresponding to the image unit corresponding to the characteristics of the signal peak; and determining the tissue type corresponding to the image unit according to the classification result.
In one embodiment, after fitting the signal peak in the variation curve using a preset function, the method further comprises: determining the fat fraction of the image unit according to the amplitude of the water peak and the amplitude of the fat peak of the image unit.
In one embodiment, the preset function includes:
wherein f (ω) is the signal intensity shown by the variation curve, a0For parameters representing the amplitude of the signal, R2Representing the transverse magnetization vector recovery rate, ω representing the frequency of the pre-saturation pulse, ω0Represents the off-resonance frequency, b1Representing the amplitude, R, of said pre-saturation pulse1Representing the longitudinal magnetization vector recovery rate.
In one embodiment, classifying the tissue type corresponding to the image unit according to the variation curve includes: inputting the change curve into a machine learning model with complete training to obtain a classification result, wherein the classification result is used for representing the tissue type corresponding to the image unit corresponding to the characteristic of the signal peak; and determining the tissue type corresponding to the image unit according to the classification result.
In a second aspect, an embodiment of the present application provides a tissue classification apparatus for magnetic resonance images, including: the application module is used for applying presaturation pulses with different preset frequency values for multiple times in an imaging visual field; the acquisition module is used for acquiring magnetic resonance data under the condition that presaturation pulses with preset frequency values are applied every time; the reconstruction module is used for reconstructing according to the magnetic resonance data to obtain a plurality of magnetic resonance amplitude images; the determining module is used for determining a change curve of the amplitude of the image unit at the same position in the plurality of magnetic resonance amplitude images and the preset frequency value according to the plurality of reconstructed magnetic resonance amplitude images; and the classification module is used for classifying the tissue types corresponding to the image units according to the change curves.
In a third aspect, an embodiment of the present application provides a magnetic resonance imaging system, including: a magnetic resonance scanner having a bore with an imaging field of view; and a processor configured to operate the magnetic resonance scanner to perform a diagnostic scan by acquiring magnetic resonance signals from a region of interest of the subject while the subject is located in the magnetic resonance scanner; wherein the processor is further configured to apply pre-saturation pulses of different preset frequency values a plurality of times in an imaging field of view; the processor further configured to acquire magnetic resonance data each time a pre-saturation pulse of a preset frequency value is applied; the processor further configured to reconstruct a plurality of magnetic resonance amplitude images from the magnetic resonance data; the processor is further configured to determine, according to a plurality of reconstructed magnetic resonance amplitude images, a variation curve of the amplitude of an image unit at the same position in the plurality of magnetic resonance amplitude images and the preset frequency value; the processor is further configured to classify the tissue type corresponding to the image unit according to the variation curve.
In a fourth aspect, the present application provides a computer-readable storage medium on which computer program instructions are stored, which when executed by a processor implement the method for tissue classification of magnetic resonance images according to the first aspect.
According to the method, the device, the storage medium and the magnetic resonance imaging system for tissue classification of magnetic resonance images, pre-saturation pulses with different preset frequency values are applied for multiple times in an imaging field, magnetic resonance data under the condition that the pre-saturation pulses with the preset frequency values are applied for each time are collected, and a plurality of magnetic resonance amplitude images are obtained through reconstruction according to the magnetic resonance data; determining a change curve of the amplitude value of the image unit at the same position in the plurality of magnetic resonance amplitude images and a preset frequency value according to the plurality of reconstructed magnetic resonance amplitude images; the method for classifying the tissue types corresponding to the image units according to the change curves solves the problem that the tissue classification method in the related technology has high requirements on the main magnetic field uniformity, and reduces the requirements of the tissue classification method on the main magnetic field uniformity.
Drawings
In order to more clearly illustrate the embodiments of the present application or technical solutions in related arts, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive efforts.
Figure 1 is a schematic structural diagram of a magnetic resonance imaging system according to an embodiment of the present application;
fig. 2 is a flow chart of a method of tissue classification of magnetic resonance images according to an embodiment of the application;
FIG. 3 is a flow chart of a method of tissue classification of magnetic resonance images according to a preferred embodiment of the present application;
FIG. 4 is a graph showing the variation of signal amplitude with offset resonance frequency in a magnetic resonance image for four different types of tissue in accordance with a preferred embodiment of the present application;
FIG. 5 is a schematic illustration of the results of tissue classification of a magnetic resonance image according to a preferred embodiment of the present application;
fig. 6 is a block diagram showing a structure of a magnetic resonance image tissue classification device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. All other examples, which can be obtained by a person skilled in the art without making any inventive step based on the examples in this application, are within the scope of protection of this application.
It is obvious that the drawings in the following description are only examples or embodiments of the application, from which the application can also be applied to other similar scenarios without inventive effort for a person skilled in the art. Moreover, it should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another.
Unless otherwise defined, technical or scientific terms used herein shall have the ordinary meaning as understood by those of ordinary skill in the art to which this application belongs. The use of "first," "second," and similar terms in the description and claims of this patent application do not denote any order, quantity, or importance, but rather the terms are used to distinguish one element from another. The terms "a," "an," "the," and the like, do not denote a limitation of quantity, and may denote the singular or plural.
The word "comprise" or "comprises", and the like, means that the element or item listed before "comprises" or "comprising" covers the element or item listed after "comprising" or "comprises" and its equivalent, and does not exclude other elements or items. "connected" or "coupled" and similar terms are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect.
"plurality" as used herein means two or more. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
The system and method of the present application can be used not only for non-invasive imaging, such as diagnosis and research of diseases, but also in the industrial field, etc., and the processing system thereof can include a magnetic resonance imaging system (MR system), a positron emission computed tomography-magnetic resonance multi-modality hybrid system (PET-MR system), etc. The methods, apparatus, systems, or computer-readable storage media described herein may be integrated with or relatively independent of the processing system described above.
The following will explain embodiments of the present application by taking a magnetic resonance imaging system as an example.
The embodiment of the application provides a magnetic resonance imaging system. Fig. 1 is a schematic structural diagram of a magnetic resonance imaging system according to an embodiment of the present application, and as shown in fig. 1, the magnetic resonance imaging system includes: a scanner and a computer, wherein the computer comprises a memory 125, a processor 122, and a computer program stored on the memory 125 and executable on the processor 122.
The scanner has a bore for the imaging field of view, which typically includes a magnetic resonance housing having a main magnet 101 therein, the main magnet 101 may be formed of superconducting coils for generating a main magnetic field, and in some cases, permanent magnets may be used. The main magnet 101 may be used to generate a main magnetic field strength of 0.2 tesla, 0.5 tesla, 1.0 tesla, 1.5 tesla, 3.0 tesla, or higher. In magnetic resonance imaging, an imaging subject 150 is carried by the patient couch 106, and as the couch plate moves, the imaging subject 150 is moved into the region 105 where the magnetic field distribution of the main magnetic field is relatively uniform. Generally, for a magnetic resonance imaging system, as shown in fig. 1, the z direction of a spatial coordinate system (i.e. a coordinate system of the magnetic resonance imaging system) is set to be the same as the axial direction of a gantry of the magnetic resonance imaging system, the length direction of a patient is generally consistent with the z direction for imaging, the horizontal plane of the magnetic resonance imaging system is set to be an xz plane, the x direction is perpendicular to the z direction, and the y direction is perpendicular to both the x and z directions.
In magnetic resonance imaging, the pulse control unit 111 controls the radio frequency pulse generating unit 116 to generate a radio frequency pulse, and the radio frequency pulse is amplified by the amplifier, passes through the switch control unit 117, and is finally emitted by the body coil 103 or the local coil 104 to perform radio frequency excitation on the imaging object 150. The imaging subject 150 generates corresponding radio frequency signals from resonance upon radio frequency excitation. When receiving the radio frequency signals generated by the imaging subject 150 according to the excitation, the radio frequency signals may be received by the body coil 103 or the local coil 104, there may be a plurality of radio frequency receiving links, and after the radio frequency signals are sent to the radio frequency receiving unit 118, the radio frequency signals are further sent to the image reconstruction unit 121 for image reconstruction, so as to form a magnetic resonance image.
The magnetic resonance scanner also includes gradient coils 102 that can be used to spatially encode the radio frequency signals in magnetic resonance imaging. The pulse control unit 111 controls the gradient signal generating unit 112 to generate gradient signals, which are generally divided into three mutually orthogonal directions: gradient signals in the x, y and z directions, which are different from each other, are amplified by gradient amplifiers (113, 114, 115) and emitted from the gradient coil 102, thereby generating a gradient magnetic field in the region 105.
The pulse control unit 111, the image reconstruction unit 121, the processor 122, the display unit 123, the input/output device 124, the memory 125 and the communication port 126 can perform data transmission through the communication bus 127, so as to realize the control of the magnetic resonance imaging process.
The processor 122 may be composed of one or more processors, and may include a Central Processing Unit (CPU), or A Specific Integrated Circuit (ASIC), or may be configured to implement one or more Integrated circuits of the embodiments of the present Application.
The display unit 123 may be a display provided to a user for displaying an image.
The input/output device 124 may be a keyboard, a mouse, a control box, or other relevant devices, and supports inputting/outputting corresponding data streams.
Among other things, the communication port 126 may enable communication with other components such as: and the external equipment, the image acquisition equipment, the database, the external storage, the image processing workstation and the like are in data communication.
Wherein the communication bus 127 comprises hardware, software, or both, coupling the components of the magnetic resonance imaging system to one another. By way of example, and not limitation, a bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hypertransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an infiniband interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a video electronics standards association local (VLB) bus, or other suitable bus or a combination of two or more of these. The communication bus 127 may include one or more buses, where appropriate. Although specific buses are described and shown in the embodiments of the application, any suitable buses or interconnects are contemplated by the application.
In some embodiments, the processor 122 is further configured to apply the presaturation pulse with different preset frequency values for a plurality of times in the imaging field of view, acquire magnetic resonance data each time the presaturation pulse with the preset frequency value is applied, and reconstruct a plurality of magnetic resonance amplitude images from the magnetic resonance data; the processor 122 is further configured to determine, according to the reconstructed magnetic resonance amplitude images, a variation curve of the amplitude of the image unit at the same position in the magnetic resonance amplitude images with a preset frequency value; the processor 122 is further configured to classify the tissue type corresponding to the image unit according to the variation curve.
In some of these embodiments, the pre-saturation pulse comprises one or more radio frequency pulses with frequency selectivity; the plurality of preset frequency values includes: a resonant frequency value and a partial resonant frequency value within a preset range at both sides of the resonant frequency value.
In some of these embodiments, the processor 122 is further configured to fit a signal peak in the variation curve using a preset function, the signal peak including: a water peak and/or a fat peak; the processor 122 is further configured to classify the tissue type corresponding to the image unit according to features of signal peaks, including: the amplitude and/or full width at half maximum of the signal peak.
In some embodiments, the processor 122 is further configured to input the features of the signal peak into a well-trained machine learning model, and obtain a classification result, where the classification result is used to represent a tissue type corresponding to an image unit corresponding to the features of the signal peak; the processor 122 is further configured to determine a tissue type corresponding to the image unit according to the classification result.
In some of these embodiments, after fitting the signal peak in the variation curve using the preset function, the method further comprises: the processor 122 is further configured to determine a fat fraction of the image cell based on the amplitude of the water peak and the amplitude of the fat peak of the image cell.
In some of these embodiments, the preset function includes:
where f (ω) is the signal intensity shown by the curve, a0For parameters representing the amplitude of the signal, R2Representing the transverse magnetization vector recovery rate, ω representing the frequency of the pre-saturation pulse, ω0Represents the off-resonance frequency, b1Representing the amplitude, R, of the pre-saturation pulse1Representing the longitudinal magnetization vector recovery rate.
In some embodiments, the processor 122 is further configured to input the variation curve into a well-trained machine learning model, and obtain a classification result, where the classification result is used to represent a tissue type corresponding to an image unit corresponding to a feature of a signal peak; the processor 122 is further configured to determine a tissue type corresponding to the image unit according to the classification result.
In the embodiment, a method for classifying tissues of a magnetic resonance image is also provided. The following describes the present embodiment by taking a magnetic resonance imaging system as an example. Fig. 2 is a flowchart of a method for tissue classification of a magnetic resonance image according to an embodiment of the present application, as shown in fig. 2, the flowchart includes the following steps:
step S201, the magnetic resonance imaging system applies presaturation pulses with different preset frequency values for multiple times in an imaging field of view, acquires magnetic resonance data under the condition that the presaturation pulses with the preset frequency values are applied every time, and reconstructs the magnetic resonance data to obtain a plurality of magnetic resonance amplitude images.
In the above steps, the magnetic resonance imaging system applies a presaturation pulse with a preset frequency value in an imaging field of view before the conventional 2D magnetic resonance imaging or the conventional 3D magnetic resonance imaging, acquires magnetic resonance data under the condition of the presaturation pulse with the preset frequency value, and reconstructs a magnetic resonance amplitude image according to the acquired magnetic resonance data. Then, the magnetic resonance imaging system changes the frequency value of the pre-saturation pulse applied in the imaging field to another preset frequency value, acquires the magnetic resonance data under the condition of the pre-saturation pulse with the another preset frequency value, and reconstructs the magnetic resonance data according to the acquired magnetic resonance data to obtain another magnetic resonance amplitude image. And analogizing until the magnetic resonance imaging system obtains magnetic resonance amplitude images under the condition of all pre-saturation pulses with preset frequency values, or the obtained magnetic resonance amplitude images reach the set number and the selected preset frequency values cover the preset range, and then executing the next step.
The Imaging sequence employed for the magnetic resonance Imaging in step S201 may be any Imaging sequence, including, but not limited to, Fast Spin Echo (FSE), Gradient Echo (GRE), Echo Planar Imaging (EPI), and any Non-Cartesian coordinate system (Non-Cartesian) acquisition. Furthermore, magnetic resonance imaging also allows the use of down-sampling techniques, i.e. the reconstruction of a magnetic resonance image based on partial K-space data without acquiring complete K-space data, resulting in the magnetic resonance amplitude image described above.
In this embodiment the magnetic resonance imaging system applies a pre-saturation pulse prior to the magnetic resonance data acquisition, which is aimed at saturating the magnetic resonance signals in whole or in part over a relatively narrow frequency range. The pre-saturation pulse may be composed of one or more Frequency selective Radio Frequency (RF) pulses, and may further include one or more saturation gradients between or after the RF pulses. The pulse energy of the pre-saturation pulse should not be too high to minimize magnetization transfer effects.
In some of these embodiments, the frequency values of the pre-saturation pulses applied by the magnetic resonance imaging system at different preset frequency values in step S201 cover the resonance frequency and the off-resonance frequency within a preset range around the resonance frequency, for example-5 ppm to +5ppm, or-3.5 ppm to +3.5 ppm. Where ppm denotes a frequency of a few parts per million of a frequency value of a center frequency point (a resonance frequency in the present embodiment), for example, -5ppm to +5ppm denotes that a preset range covered by the preset frequency value is in a range of 0.9995% to 1.0005% of the resonance frequency value.
The magnetic resonance image reconstruction method employed by the magnetic resonance imaging system in step S201 may employ any magnetic resonance image reconstruction technique, including but not limited to one of the following:
(1) conventional method, parallel imaging method. For example, generalized auto-calibration partial Parallel acquisition (GRAPPA), etc., the data obtained at each off-resonance frequency (i.e., the frequency of the pre-saturation pulse) in step S201 is respectively subjected to imaging reconstruction.
(2) A high-level method. Such as key-hold, compressed sensing, etc. The data of all the partial resonance frequencies can be reconstructed together by adopting a high-level method, the data of different partial resonance frequencies can obviously or implicitly borrow the data of other partial resonance frequencies during reconstruction, and finally, a series of 2D or 3D magnetic resonance amplitude images under different partial resonance frequencies are reconstructed.
Step S202, the magnetic resonance imaging system determines a variation curve of the amplitude and a preset frequency value of the image unit at the same position in the plurality of magnetic resonance amplitude images according to the plurality of reconstructed magnetic resonance amplitude images.
The series of magnetic resonance amplitude images obtained in step S201 may be 2D magnetic resonance amplitude images or 3D magnetic resonance amplitude images according to different magnetic resonance imaging modes. In step S202, the magnetic resonance imaging system calculates a variation curve of the amplitudes of the image units at the same positions in the magnetic resonance amplitude images along with the preset frequency value of the presaturation pulse according to the plurality of reconstructed magnetic resonance amplitude images, so as to obtain a response result of each image unit in the magnetic resonance amplitude images to the off-resonance frequency. The image unit refers to a component unit of a magnetic resonance amplitude image, the image unit is a pixel in a 2D magnetic resonance amplitude image, and the image unit is a voxel in a 3D magnetic resonance amplitude image.
Step S203, the magnetic resonance imaging system classifies the tissue types corresponding to the image units according to the variation curve.
The amplitude of an image unit in the magnetic resonance amplitude image is mainly formed by overlapping the amplitude of a water signal and the amplitude of a fat signal; while different types of tissue have different water signal intensity (or proportion of water to tissue) and fat signal intensity (or proportion of fat to tissue, also known as fat fraction). Therefore, according to the change curve of the amplitude of the image unit along with the preset frequency value of the pre-saturation pulse, the characteristics of the water signal and the fat signal of the tissue where the image unit is located are obtained, and the tissue type can be classified according to the characteristics. Compared with the tissue classification method in which the water-fat separation technology in the related art can only distinguish water and fat components, by adopting the steps S201 to S203 in the embodiment of the present application, more precise tissue classification can be realized according to the ratio of water and fat in different types of tissues (e.g., lung tissue and brain tissue), or the characteristics of the water signal and the fat signal, or the characteristics of the superimposed signal of the water signal and the fat signal. Moreover, the steps S201 to S203 in the embodiment of the present application do not depend on a specific magnetic resonance data acquisition method and a specific magnetic resonance image reconstruction method, so that a suitable magnetic resonance data acquisition method and a suitable magnetic resonance image reconstruction method can be selected according to an application scene and a scanning part, and adverse effects caused by nonuniformity of a main magnetic field are reduced, thereby realizing adaptation to various application scenes and reducing requirements of a tissue classification method on main magnetic field uniformity.
Fig. 3 is a flow chart of a method for tissue classification of a magnetic resonance image according to a preferred embodiment of the present application, as shown in fig. 3, wherein in some embodiments the flow of the method for tissue classification of a magnetic resonance image comprises the following steps:
step S301, the magnetic resonance imaging system applies presaturation pulses with different preset frequency values for multiple times in an imaging field of view, acquires magnetic resonance data under the condition that the presaturation pulses with the preset frequency values are applied every time, and reconstructs the magnetic resonance data to obtain a plurality of magnetic resonance amplitude images.
Step S302, the magnetic resonance imaging system determines a variation curve of the amplitude value and a preset frequency value of the image unit at the same position in the plurality of magnetic resonance amplitude images according to the plurality of reconstructed magnetic resonance amplitude images.
Step S303, the magnetic resonance imaging system uses a preset function to fit a signal peak in the variation curve, where the signal peak includes: water peak and/or fat peak.
The amplitude of the image unit in the magnetic resonance amplitude image is mainly formed by the superposition of the water signal amplitude and the fat signal amplitude. Through experimental statistics, the amplitude of an image unit in a magnetic resonance amplitude image is related to magnetic resonance imaging parameters such as partial resonance frequency and the like. Therefore, the signal peak in step S302 is fitted with a preset function that can characterize the amplitude, off-resonance frequency and other magnetic resonance imaging parameter interrelations of the image elements in the magnetic resonance amplitude image.
The preset function in this embodiment is typically obtained by the monte carlo method. The magnetic resonance imaging parameters in this embodiment include, but are not limited to, at least one of: longitudinal relaxation time, transverse relaxation time, longitudinal magnetization vector recovery rate, transverse magnetization vector recovery rate, partial resonance frequency. Wherein the longitudinal relaxation time and the longitudinal magnetization vector recovery rate are reciprocal to each other, and the transverse relaxation time and the transverse magnetization vector recovery rate are reciprocal to each other.
In the present embodiment, a preset function is provided to obtain the off-resonance frequency, the transverse relaxation time (or transverse magnetization vector recovery rate), and the longitudinal relaxation time (or longitudinal magnetization vector recovery rate) of the corresponding image unit. The preset function is expressed as follows:
where f (ω) is the signal intensity shown by the curve, a0For parameters representing the amplitude of the signal, R2Representing the transverse magnetization vector recovery rate, ω representing the frequency of the pre-saturation pulse, ω0Represents the off-resonance frequency, b1Representing the amplitude, R, of the pre-saturation pulse1Representing the longitudinal magnetization vector recovery rate.
In the above formula, f, b1ω is a known quantity, and R can be obtained by curve fitting2、R1、ω0The numerical value of (c).
Moreover, when the magnetic resonance imaging system performs curve fitting, only a water peak consisting of water signals can be generally fitted; it is also possible to fit both a water peak consisting of a water signal and a fat peak consisting of a fat signal. However, considering the efficiency of curve fitting and reducing the computer resources occupied by curve fitting, the signal peak corresponding to the signal with stronger signal intensity can be selected for curve fitting according to the intensity of the water signal and the fat signal.
Step S304, the magnetic resonance imaging system classifies the tissue types corresponding to the image unit according to the characteristics of the signal peak, and the characteristics of the signal peak comprise: the amplitude and/or full width at half maximum of the signal peak.
In step S303, after the magnetic resonance imaging parameters are obtained by curve fitting, the variation curve of the water signal and/or the fat signal can be separated from the variation curve of the superimposed signal, so that the tissue types corresponding to the image unit can be classified according to the features of the water peak and/or the fat peak.
Fig. 4 is a graph showing the variation of signal amplitude with offset resonance frequency in a magnetic resonance image for four different types of tissues according to the preferred embodiment of the present application. In these change curves, the horizontal axis corresponding to the position of the vertical dotted line represents the resonance frequency, the horizontal axis represents the unit ppm, and the vertical axis represents the signal amplitude intensity. Wherein, in the b) diagram of fig. 4, the fat signal is negligible, i.e. the b) diagram of fig. 4 can be basically considered as the variation curve (i.e. water peak) of the water signal. Then in the b) diagram of fig. 4, the amplitude and/or full width at half maximum of the water peak can be used as its characteristic and the tissue type can be determined from the characteristic.
In some embodiments, the features and the tissue types corresponding to the features may be obtained in advance through a statistical method, or the features of different types of tissues may be learned through a machine learning method and automatic classification may be implemented. For example, in some embodiments, the classification of the tissue type corresponding to the image unit according to the feature of the signal peak may be performed by inputting the feature of the signal peak into a machine learning model with complete training to obtain a classification result, where the classification result is used to represent the tissue type corresponding to the image unit corresponding to the feature of the signal peak; and determining the tissue type corresponding to the image unit according to the classification result.
The machine learning model used in the method can be a machine learning model based on a deep learning algorithm, such as various artificial neural network models, or a machine learning model based on a shallow learning algorithm, such as a support vector machine model and a decision tree model. Moreover, in the case where the features used for classification are known in the above embodiment, the use of a machine learning model based on a shallow learning algorithm can reduce the model training overhead.
It should be noted that, the machine learning model and the training method thereof employed in the present embodiment may employ known techniques.
In some of the embodiments, after the signal peaks in the variation curve are fitted using the preset function, in case that the signal peaks include a water peak and a fat peak, the fat fraction of the image unit may be further determined according to the amplitudes of the water peak and the fat peak of the image unit. The fat score may also serve as a basis for classification or one of the classifications of tissue types.
After the tissue type corresponding to each image unit according to the above-described embodiment, a magnetic resonance image classified by tissue type can be obtained. Fig. 5 is a schematic diagram of the tissue classification result of the magnetic resonance image according to the preferred embodiment of the present application, as shown in fig. 5, which sequentially shows a) a water image, b) a fat image and c) a fat fraction image from left to right. The image in fig. 5 shows dark to light that the proportion of the corresponding component is 0% to 100%, respectively.
In some embodiments, after obtaining the variation curves of the amplitudes of the image units at the same positions in the plurality of magnetic resonance amplitude images and the preset frequency values in step S202 or step S302, the magnetic resonance imaging system may further input the variation curve of each image unit into a machine learning model which is trained completely, so as to obtain a classification result, where the classification result is used to represent a tissue type corresponding to the image unit corresponding to the feature of the signal peak; and then the magnetic resonance imaging system determines the tissue type corresponding to the image unit according to the classification result.
In the embodiment, the variation curve of the amplitude and the preset frequency value of the image unit at the same position in the magnetic resonance amplitude image is directly input into the machine learning model, especially an artificial neural network model with feature extraction capability is adopted, so that the feature extraction step of the variation curve is simplified.
In this embodiment, a tissue classification device for magnetic resonance images is further provided, and the device is used to implement the above embodiments and preferred embodiments, which have already been described and will not be described again. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. While the system described in the embodiments below is preferably implemented in software, implementations in hardware, or a combination of software and hardware are also possible and contemplated.
Fig. 6 is a block diagram of a magnetic resonance image tissue classification apparatus according to an embodiment of the present application, and as shown in fig. 6, the apparatus includes:
an applying module 61, configured to apply presaturation pulses with different preset frequency values for multiple times in an imaging field of view;
an acquisition module 62, coupled to the application module 61, for acquiring magnetic resonance data each time a presaturation pulse of a preset frequency value is applied;
a reconstruction module 63, coupled to the acquisition module 62, configured to reconstruct a plurality of magnetic resonance amplitude images according to the magnetic resonance data;
a determining module 64, coupled to the reconstructing module 63, configured to determine, according to the multiple magnetic resonance amplitude images obtained through reconstruction, a variation curve between the amplitude of the image unit at the same position in the multiple magnetic resonance amplitude images and a preset frequency value;
a classification module 65, coupled to the determination module 64, for classifying the tissue types corresponding to the image units according to the variation curve.
In some of these embodiments, the pre-saturation pulse comprises one or more radio frequency pulses with frequency selectivity; the plurality of preset frequency values includes: a resonant frequency value and a partial resonant frequency value within a preset range at both sides of the resonant frequency value.
In some of these embodiments, classification module 65 includes: a fitting unit for fitting a signal peak in the variation curve using a preset function, the signal peak including: a water peak and/or a fat peak; and the classification unit is coupled to the fitting unit and used for classifying the tissue types corresponding to the image unit according to the characteristics of the signal peak, wherein the characteristics of the signal peak comprise: the amplitude and/or full width at half maximum of the signal peak.
In some of these embodiments, the classification unit comprises: the input subunit is coupled to the fitting unit and is used for inputting the characteristics of the signal peak into a machine learning model with complete training to obtain a classification result, and the classification result is used for representing the tissue type corresponding to the image unit corresponding to the characteristics of the signal peak; and the determining subunit is coupled to the input subunit and used for determining the tissue type corresponding to the image unit according to the classification result.
In some of these embodiments, classification module 65 further includes: and the first determining unit is coupled between the fitting unit and the classifying unit and used for determining the fat fraction of the image unit according to the amplitude of the water peak and the amplitude of the fat peak of the image unit.
In some of these embodiments, the preset function includes:
where f (ω) is the signal intensity shown by the curve, a0For parameters representing the amplitude of the signal, R2Representing the transverse magnetization vector recovery rate, ω representing the frequency of the pre-saturation pulse, ω0Represents the off-resonance frequency, b1Representing the amplitude, R, of the pre-saturation pulse1Representing the longitudinal magnetization vector recovery rate.
In some of these embodiments, classification module 65 includes: the input unit is used for inputting the change curve into a machine learning model with complete training to obtain a classification result, and the classification result is used for representing the tissue type corresponding to the image unit corresponding to the characteristic of the signal peak; and the second determining unit is coupled to the input unit and used for determining the tissue type corresponding to the image unit according to the classification result.
In addition, in combination with the tissue classification method for magnetic resonance images in the above embodiments, the embodiments of the present application may be implemented by providing a computer-readable storage medium. The computer readable storage medium having stored thereon computer program instructions; the computer program instructions, when executed by a processor, implement a method of tissue classification of a magnetic resonance image as in any one of the above embodiments.
In summary, according to some embodiments or preferred embodiments of the present application, a series of variable-frequency pre-saturation pulses are implemented during magnetic resonance imaging of a human body, and then features are extracted from a variation curve of an image unit by a model fitting manner or a machine learning algorithm to perform tissue classification, so that a problem that a tissue classification method in the related art has a high requirement on main magnetic field uniformity is solved, and a requirement of the tissue classification method on main magnetic field uniformity is reduced.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method of tissue classification in a magnetic resonance image, comprising:
applying presaturation pulses with different preset frequency values for multiple times in an imaging visual field, acquiring magnetic resonance data under the condition that the presaturation pulses with the preset frequency values are applied every time, and reconstructing according to the magnetic resonance data to obtain a plurality of magnetic resonance amplitude images;
determining a change curve of the amplitude of the image unit at the same position in the plurality of magnetic resonance amplitude images and the preset frequency value according to the plurality of reconstructed magnetic resonance amplitude images;
and classifying the tissue types corresponding to the image units according to the change curves.
2. The method of tissue classification of a magnetic resonance image according to claim 1, characterized in that the pre-saturation pulses comprise one or more frequency selective radio frequency pulses; the plurality of preset frequency values comprises: a resonant frequency value and a partial resonant frequency value in a preset range at both sides of the resonant frequency value.
3. The method of classifying tissue according to claim 1, wherein classifying the tissue type corresponding to the image unit according to the variation curve comprises:
fitting a signal peak in the variation curve using a preset function, the signal peak comprising: a water peak and/or a fat peak;
classifying the tissue type corresponding to the image unit according to the characteristics of the signal peak, wherein the characteristics of the signal peak comprise: the amplitude and/or full width at half maximum of the signal peak.
4. The method of claim 3, wherein classifying the tissue type corresponding to the image unit according to the feature of the signal peak comprises:
inputting the characteristics of the signal peak into a machine learning model with complete training to obtain a classification result, wherein the classification result is used for representing the tissue type corresponding to the image unit corresponding to the characteristics of the signal peak;
and determining the tissue type corresponding to the image unit according to the classification result.
5. The method of tissue classification of a magnetic resonance image according to claim 3, characterized in that after fitting the signal peaks in the variation curve using a preset function, the method further comprises:
determining the fat fraction of the image unit according to the amplitude of the water peak and the amplitude of the fat peak of the image unit.
6. The method of tissue classification of a magnetic resonance image according to claim 3, characterized in that the preset function comprises:
wherein f (ω) is the signal intensity shown by the variation curve, a0For parameters representing the amplitude of the signal, R2Representing the transverse magnetization vector recovery rate, ω representing the frequency of the pre-saturation pulse, ω0Represents the off-resonance frequency, b1Representing the amplitude, R, of said pre-saturation pulse1Representing the longitudinal magnetization vector recovery rate.
7. The method of classifying tissue according to claim 1, wherein classifying the tissue type corresponding to the image unit according to the variation curve comprises:
inputting the change curve into a machine learning model with complete training to obtain a classification result, wherein the classification result is used for representing the tissue type corresponding to the image unit corresponding to the characteristic of the signal peak;
and determining the tissue type corresponding to the image unit according to the classification result.
8. An apparatus for tissue classification of a magnetic resonance image, comprising:
the application module is used for applying presaturation pulses with different preset frequency values for multiple times in an imaging visual field;
the acquisition module is used for acquiring magnetic resonance data under the condition that presaturation pulses with preset frequency values are applied every time;
the reconstruction module is used for reconstructing according to the magnetic resonance data to obtain a plurality of magnetic resonance amplitude images;
the determining module is used for determining a change curve of the amplitude of the image unit at the same position in the plurality of magnetic resonance amplitude images and the preset frequency value according to the plurality of reconstructed magnetic resonance amplitude images;
and the classification module is used for classifying the tissue types corresponding to the image units according to the change curves.
9. A magnetic resonance imaging system, characterized in that the magnetic resonance imaging system comprises: a magnetic resonance scanner having a bore with an imaging field of view; and a processor configured to operate the magnetic resonance scanner to perform a diagnostic scan by acquiring magnetic resonance signals from a region of interest of the subject while the subject is located in the magnetic resonance scanner; wherein the content of the first and second substances,
the processor further configured to apply pre-saturation pulses of different preset frequency values a plurality of times in an imaging field of view;
the processor further configured to acquire magnetic resonance data each time a pre-saturation pulse of a preset frequency value is applied;
the processor further configured to reconstruct a plurality of magnetic resonance amplitude images from the magnetic resonance data;
the processor is further configured to determine, according to a plurality of reconstructed magnetic resonance amplitude images, a variation curve of the amplitude of an image unit at the same position in the plurality of magnetic resonance amplitude images and the preset frequency value;
the processor is further configured to classify the tissue type corresponding to the image unit according to the variation curve.
10. A computer-readable storage medium, on which computer program instructions are stored, which, when executed by a processor, implement a method of tissue classification of a magnetic resonance image as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911347737.XA CN111044958B (en) | 2019-12-24 | 2019-12-24 | Tissue classification method, device, storage medium and magnetic resonance imaging system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911347737.XA CN111044958B (en) | 2019-12-24 | 2019-12-24 | Tissue classification method, device, storage medium and magnetic resonance imaging system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111044958A true CN111044958A (en) | 2020-04-21 |
| CN111044958B CN111044958B (en) | 2022-03-25 |
Family
ID=70238813
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911347737.XA Active CN111044958B (en) | 2019-12-24 | 2019-12-24 | Tissue classification method, device, storage medium and magnetic resonance imaging system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111044958B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023108325A1 (en) * | 2021-12-13 | 2023-06-22 | 中国科学院深圳先进技术研究院 | Fat quantitative imaging method and apparatus, and device and storage medium thereof |
| WO2023216582A1 (en) * | 2022-05-12 | 2023-11-16 | 深圳先进技术研究院 | Magnetic resonance chemical exchange saturation transfer imaging method, system and device |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5551431A (en) * | 1994-10-04 | 1996-09-03 | The Brigham And Women's Hospital, Inc. | Correction of magnetic resonance imager intensity inhomogeneities using tissue properties |
| CN102920455A (en) * | 2011-01-27 | 2013-02-13 | 美国西门子医疗解决公司 | A method for independent manipulation of a fat and a water component in magnetic resonance imaging |
| CN103167829A (en) * | 2011-10-13 | 2013-06-19 | 株式会社东芝 | Magnetic resonance imaging device and magnetic resonance imaging method |
| CN104379057A (en) * | 2012-08-31 | 2015-02-25 | 株式会社东芝 | Magnetic resonance imaging device |
| CN105572613A (en) * | 2014-10-13 | 2016-05-11 | 中国科学院深圳先进技术研究院 | Magnetic resonance chemical exchange saturation transfer imaging method and magnetic resonance chemical exchange saturation transfer imaging system |
| CN106466182A (en) * | 2015-08-18 | 2017-03-01 | 上海联影医疗科技有限公司 | MR imaging method and system |
| CN107015181A (en) * | 2017-04-07 | 2017-08-04 | 厦门大学 | A kind of method that proton longitudinal relaxation time is measured under non-uniform magnetic field |
| CN107656225A (en) * | 2017-10-31 | 2018-02-02 | 上海联影医疗科技有限公司 | Magnetic resonance frequency calibration method, MR imaging method and system |
| CN107997763A (en) * | 2017-12-26 | 2018-05-08 | 中国科学院生物物理研究所 | A kind of water fat separates MR imaging method |
| CN108209918A (en) * | 2017-12-30 | 2018-06-29 | 上海联影医疗科技有限公司 | MR imaging method and magnetic resonance system |
| CN108720834A (en) * | 2018-02-06 | 2018-11-02 | 苏州朗润医疗系统有限公司 | A kind of magnetic resonance imaging system of the more echo water fat separation methods of gtadient echo and application this method |
| CN109709503A (en) * | 2019-02-13 | 2019-05-03 | 上海联影医疗科技有限公司 | A kind of magnetic resonance system control method, magnetic resonance system, computer equipment |
-
2019
- 2019-12-24 CN CN201911347737.XA patent/CN111044958B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5551431A (en) * | 1994-10-04 | 1996-09-03 | The Brigham And Women's Hospital, Inc. | Correction of magnetic resonance imager intensity inhomogeneities using tissue properties |
| CN102920455A (en) * | 2011-01-27 | 2013-02-13 | 美国西门子医疗解决公司 | A method for independent manipulation of a fat and a water component in magnetic resonance imaging |
| CN103167829A (en) * | 2011-10-13 | 2013-06-19 | 株式会社东芝 | Magnetic resonance imaging device and magnetic resonance imaging method |
| CN104379057A (en) * | 2012-08-31 | 2015-02-25 | 株式会社东芝 | Magnetic resonance imaging device |
| CN105572613A (en) * | 2014-10-13 | 2016-05-11 | 中国科学院深圳先进技术研究院 | Magnetic resonance chemical exchange saturation transfer imaging method and magnetic resonance chemical exchange saturation transfer imaging system |
| CN106466182A (en) * | 2015-08-18 | 2017-03-01 | 上海联影医疗科技有限公司 | MR imaging method and system |
| CN107015181A (en) * | 2017-04-07 | 2017-08-04 | 厦门大学 | A kind of method that proton longitudinal relaxation time is measured under non-uniform magnetic field |
| CN107656225A (en) * | 2017-10-31 | 2018-02-02 | 上海联影医疗科技有限公司 | Magnetic resonance frequency calibration method, MR imaging method and system |
| CN107997763A (en) * | 2017-12-26 | 2018-05-08 | 中国科学院生物物理研究所 | A kind of water fat separates MR imaging method |
| CN108209918A (en) * | 2017-12-30 | 2018-06-29 | 上海联影医疗科技有限公司 | MR imaging method and magnetic resonance system |
| CN108720834A (en) * | 2018-02-06 | 2018-11-02 | 苏州朗润医疗系统有限公司 | A kind of magnetic resonance imaging system of the more echo water fat separation methods of gtadient echo and application this method |
| CN109709503A (en) * | 2019-02-13 | 2019-05-03 | 上海联影医疗科技有限公司 | A kind of magnetic resonance system control method, magnetic resonance system, computer equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023108325A1 (en) * | 2021-12-13 | 2023-06-22 | 中国科学院深圳先进技术研究院 | Fat quantitative imaging method and apparatus, and device and storage medium thereof |
| WO2023216582A1 (en) * | 2022-05-12 | 2023-11-16 | 深圳先进技术研究院 | Magnetic resonance chemical exchange saturation transfer imaging method, system and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111044958B (en) | 2022-03-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111656392B (en) | System and method for synthesizing magnetic resonance images | |
| CN107072592B (en) | Magnetic resonance imaging apparatus and quantitative magnetic susceptibility matching method | |
| US10705168B2 (en) | System and method for low rank approximation of high resolution MRF through dictionary fitting | |
| EP3201643B1 (en) | Magnetic resonance imaging with enhanced bone visualization | |
| JP6417406B2 (en) | MR imaging with enhanced susceptibility contrast | |
| US9799120B1 (en) | Method and apparatus for atlas/model-based segmentation of magnetic resonance images with weakly supervised examination-dependent learning | |
| CN108778116A (en) | MR imaging apparatus and image processing method | |
| US20120176131A1 (en) | System and method for fat suppression in chemical shift based water-fat separated mr imaging | |
| CN106232002B (en) | The EPT method that the conductivity of stability and speed with enhancing is rebuild | |
| CN111044958B (en) | Tissue classification method, device, storage medium and magnetic resonance imaging system | |
| Jog et al. | Random forest flair reconstruction from t 1, t 2, and p d-weighted mri | |
| Mani et al. | Model-based deep learning for reconstruction of joint kq under-sampled high resolution diffusion MRI | |
| US10664683B2 (en) | Method and apparatus for classifying magnetic resonance measurement data acquired from an examination object using a magnetic resonance fingerprinting method | |
| CN110940943B (en) | Training method of pulsation artifact correction model and pulsation artifact correction method | |
| CN111275783B (en) | Phase unwrapping method and device of magnetic resonance image and magnetic resonance imaging system | |
| CN111044957B (en) | Magnetic resonance imaging method, magnetic resonance imaging device, storage medium and magnetic resonance imaging system | |
| US11864863B2 (en) | System, method and computer-accessible medium for accelerated, simultaneous quantitative and non-synthetic multi-contrast imaging | |
| Naguliak et al. | The influence of the time MR sequence parameters on the diffusion weighted imaging sensitivity | |
| Netreba et al. | Correlation reconstructed spine and time relaxation spatial distribution of atomic systems in MRI | |
| EP4174868A1 (en) | Synthetic contrast-enhanced mr images | |
| WO2024015470A1 (en) | Simulating structures in images | |
| Karaman et al. | Temporal processing of fMRI data induces functional correlations and potentially alters functional activations | |
| Khazen et al. | Excitation Independent Fat Suppression for DCE MRI of breast cancer, using a multivariate statistical approach | |
| Joshi et al. | MRI Denoising for Healthcare | |
| CN113133756A (en) | Three-dimensional cardiac cine imaging method, magnetic resonance imaging system and storage medium |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 201807 Shanghai City, north of the city of Jiading District Road No. 2258 Applicant after: Shanghai Lianying Medical Technology Co., Ltd Address before: 201807 Shanghai City, north of the city of Jiading District Road No. 2258 Applicant before: SHANGHAI UNITED IMAGING HEALTHCARE Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |