CN114565690A - Magnetic resonance imaging method based on wave gradient coding field and deep learning model - Google Patents

Abstract

The present application discloses a magnetic resonance imaging method, device, device and storage medium based on a wave (Wave-CAIPI) coding gradient field and a deep learning model. The method includes: a magnetic resonance reconstruction model in the Wave-CAIPI gradient coding field The deep generative network model (DGM) is introduced to accelerate the magnetic resonance imaging; the physical coil channel data is conjugated symmetrically through the virtual conjugate coil (VCC) to generate the VCC channel data; the physical coil channel data and the VCC channel data are combined to reconstruct the geometry factor calculation model. The above solution provided in this application combines VCC (Wave-CAIPI) technology and DGM in the case of Wave-CAIPI gradient coding. It is smaller and more uniform, so that the reconstructed graph has a higher signal-to-noise ratio and shortens the steps of training network parameters in traditional convolutional neural networks that require a large amount of training data.

Description

Magnetic resonance imaging method based on wave gradient coding field and deep learning model

technical field

The invention relates to the technical field of magnetic resonance imaging, in particular to a magnetic resonance imaging method, device, device and storage medium based on a wave gradient coding field and a deep learning model.

Background technique

In conventional magnetic resonance imaging (MRI), long scan times are inherent. Among the existing magnetic resonance imaging acceleration methods, parallel imaging is an effective method for accelerating imaging. Parallel imaging is a method that utilizes the spatial encoding capability of multi-channel phased array coils to reduce the number of encoding steps of the gradient magnetic field and achieve acceleration. In practice, parallel imaging achieves the purpose of undersampling through redundant information (a priori information) during multi-channel k-space. In parallel imaging, reconstruction methods can be divided into two categories, one is based on image domain antialiasing or solving methods, such as PILS, SENSE and ESPIRiT, etc.; the other is based on k-space data filling methods, such as SMASH, GRAPPA and SPIRiT et al. In the reconstruction method in the image domain, firstly, the acquired k-space reference line (ACS) is used to estimate the coil sensitivity information (CSM). CSM performs antialiasing; a method based on k-space data padding, similar to the method in the image domain, estimates the convolution kernel for padding the k-space raw data through the collected ACS lines. Whether it is an acceleration method based on the image domain or based on k-space, the ACS line needs to be collected for estimating the CSM or the kernel. Then it takes a lot of time to acquire ACS in practice, and it takes a lot of time to estimate the CSM or the kernel using a common algorithm (such as ESPIRiT, etc.) after the acquisition of the ACS line, which is not friendly to practical applications.

A parallel imaging method with controllable aliasing using Wave-CAIPI (where CAIPI means controlling the phase to shift or displace operations in the phase and slice selection directions) has a remarkable effect in 3D imaging by causing Aliasing, which takes full advantage of coil sensitivity changes in three directions, significantly reduces geometry factors and residual aliasing artifacts for high-power accelerated 3D imaging. Wave-CAIPI combines beam phase encoding (BPE) and controllable aliasing parallel imaging (CAIPIRINHA), which can significantly utilize the CSM information aliased in three directions in space, and use the extended SENSE model to solve, the system has a smaller condition number , so that the reconstructed geometric factor is smaller and the distribution is more uniform, so that the reconstructed image has a higher signal-to-noise ratio. Although Wave-CAIPI can achieve a higher speedup while taking into account a higher signal-to-noise ratio, the reconstruction process still needs to acquire the ACS to estimate the CSM. This process still does not avoid the time-consuming process based on the image domain or k-space. It is not friendly in clinical application.

SUMMARY OF THE INVENTION

In view of the above-mentioned defects or deficiencies in the prior art, it is desirable to provide a magnetic resonance imaging method, apparatus, device and storage medium based on the Wave-CAIPI gradient coding field and the deep learning model.

In a first aspect, an embodiment of the present application provides a magnetic resonance imaging method based on the Wave-CAIPI deep learning model, the method includes: introducing a deep generative network model into the magnetic resonance reconstruction model of the Wave-CAIPI gradient coding field to accelerate magnetic resonance imaging. Resonance imaging; make conjugate symmetry to the physical coil channel data through VCC to generate VCC channel data; combine the physical coil channel data and the VCC channel data to reconstruct the geometric factor calculation model.

In one of the embodiments, before the deep generative network model is introduced into the magnetic resonance reconstruction model of the Wave-CAIPI gradient coding field, the method further includes: using parallel imaging to acquire a plurality of images corresponding to different channels in accelerated magnetic resonance imaging Under-sampled k-space, based on different coil sensitivity information, an artifact-free image of the reconstructed under-sampled k-space is obtained.

M表示在相位编码方向由可控混叠并行成像采样模式导致的偏移混叠，F_x表示在x方向的傅里叶变换，S表示线圈敏感度信息，Psf(k_x,y,z)为Wave－CAIPI梯度场的作用效果；通过wave(x,y,z)＝Em(x,y,z)和

得到

其中，Psf[x,y,z]为Psf(k_x,y,z)在读出方向的反傅里叶变换。In one embodiment, the introduction of a deep generative network model into the magnetic resonance reconstruction model of the Wave-CAIPI gradient coding field to accelerate the magnetic resonance imaging includes: establishing a coding model of the Wave gradient field (Wave) in the magnetic resonance imaging: wave(x,y,z)=Em(x,y,z), where E is the encoding matrix,

M represents the offset aliasing caused by the controllable aliasing parallel imaging sampling mode in the phase encoding direction, F _x represents the Fourier transform in the x direction, S represents the coil sensitivity information, Psf(k _x ,y,z) is the effect of the Wave-CAIPI gradient field; through wave(x,y,z)=Em(x,y,z) and

get

Among them, Psf[x,y,z] is the inverse Fourier transform of Psf(k _x ,y,z) in the readout direction.

得到

其中，wave^*(x,y,z)表示通过VCC扩展后的数据，

表示在现有的Psf[x,y,z]基础上扩展通道数的Psf。In one of the embodiments, performing conjugate symmetry on the physical coil channel data through VCC to generate the VCC channel data includes: using wave(x, y, z)=Em(x, y, z) and

get

Among them, wave ^* (x,y,z) represents the data expanded by VCC,

Represents a Psf that extends the number of channels based on the existing Psf[x,y,z].

In one embodiment, after generating the VCC channel data, the method further includes: introducing a deep generative model that does not require training.

得到经过VCC扩展后的几何因子g－factor，其中，

表示经过VCC扩展后的编码矩阵。In one embodiment, the reconstructing the geometric factor calculation model by combining the physical coil channel data and the VCC channel data includes: using the formula

The geometric factor g-factor after VCC expansion is obtained, where,

Indicates the encoding matrix after VCC expansion.

In a second aspect, the embodiments of the present application further provide a magnetic resonance imaging device based on the Wave-CAIPI gradient coding field and a deep learning model, the device comprising: an introduction unit for MR reconstruction in the Wave-CAIPI gradient coding field The deep generation network model is introduced into the model to accelerate magnetic resonance imaging; the generation unit is used to make conjugate symmetry of the physical coil channel data through VCC to generate the VCC channel data; the reconstruction unit is used to combine the physical coil channel data and the VCC channel data. Rebuild the geometric factor calculation model.

In a third aspect, an embodiment of the present application further provides a computer device, including a memory, a processor, and a computer program stored in the memory and running on the processor, the processor implementing the program as described in the present application when the processor executes the program. A method as in any one of the descriptions of the embodiments.

In a fourth aspect, an embodiment of the present application further provides a computer device, a computer-readable storage medium, on which a computer program is stored, and the computer program is used for: when the computer program is executed by a processor, the computer program is executed as described in the present application. A method as in any one of the descriptions of the embodiments.

Beneficial effects of the present invention:

The magnetic resonance imaging method based on the Wave-CAIPI gradient coding field and the deep learning model provided by the present invention combines Wave-CAIPI, VCC and DGM, which not only utilizes the advantages of Wave-CAIPI and VCC to reduce the system condition number, but also applies The reconstructed g-factor is smaller and more uniform, so the reconstructed graph has a higher signal-to-noise ratio, and in the process of solving, it is not necessary to collect ACS lines to estimate CSM or kernel, which greatly shortens the traditional convolutional neural network. The training data trains the data acquisition time of network parameters, and avoids errors caused by inaccurate acquisition data, and does not require time-consuming estimation of CSM or kernel in traditional reconstruction, which is more suitable for clinical needs.

Description of drawings

Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

FIG. 1 shows a schematic flowchart of a magnetic resonance imaging method based on a Wave-CAIPI gradient coding field and a deep learning model provided by an embodiment of the present application;

FIG. 2 shows an exemplary structural block diagram of a magnetic resonance imaging apparatus 200 based on a Wave-CAIPI gradient coding field and a deep learning model according to an embodiment of the present application;

FIG. 3 shows a schematic structural diagram of a computer system suitable for implementing a terminal device according to an embodiment of the present application;

FIG. 4 shows a structural diagram of a deep generative model provided by an embodiment of the present application;

FIG. 5 shows a schematic diagram of a simulation result combining Wave-CAIPI and VCC provided by an embodiment of the present application;

FIG. 6 shows a schematic diagram of a reconstruction comparison result of WV-DGM and WV-SENSE (Wave-VCC SENSE) on brain data provided by an embodiment of the present application.

Detailed ways

In order to make the above objects, features and advantages of the present invention more clearly understood, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. However, the present invention can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", " Back, Left, Right, Vertical, Horizontal, Top, Bottom, Inner, Outer, Clockwise, Counterclockwise, Axial , "radial", "circumferential" and other indicated orientations or positional relationships are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying the indicated device or Elements must have a particular orientation, be constructed and operate in a particular orientation and are therefore not to be construed as limitations of the invention.

In addition, the terms "first" and "second" are only used for descriptive purposes, and should not be construed as indicating or implying relative importance or implying the number of indicated technical features. Thus, a feature delimited with "first", "second" may expressly or implicitly include at least one of that feature. In the description of the present invention, "plurality" means at least two, such as two, three, etc., unless otherwise expressly and specifically defined.

In the present invention, unless otherwise expressly specified and limited, the terms "installed", "connected", "connected", "fixed" and other terms should be understood in a broad sense, for example, it may be a fixed connection or a detachable connection , or integrated; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between the two elements, unless otherwise specified limit. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

In the present invention, unless otherwise expressly specified and limited, a first feature "on" or "under" a second feature may be in direct contact between the first and second features, or the first and second features indirectly through an intermediary touch. Also, the first feature being "above", "over" and "above" the second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is level higher than the second feature. The first feature being "below", "below" and "below" the second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature has a lower level than the second feature.

It should be noted that when an element is referred to as being "fixed to" or "disposed on" another element, it can be directly on the other element or an intervening element may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. The terms "vertical", "horizontal", "upper", "lower", "left", "right" and similar expressions used herein are for the purpose of illustration only and do not represent the only embodiment.

Please refer to FIG. 1 , which shows a schematic flowchart of a magnetic resonance imaging method based on a Wave-CAIPI gradient coding field and a deep learning model provided by an embodiment of the present application.

As shown in Figure 1, the method includes:

Step 110: Introduce a deep generative network model into the magnetic resonance reconstruction model of the Wave-CAIPI gradient coding field to accelerate magnetic resonance imaging;

Step 120: Conjugate the physical coil channel data through VCC to generate VCC channel data;

Step 130 , combine the physical coil channel data and the VCC channel data to reconstruct a geometric factor calculation model.

Using the above technical solution, combining Wave-CAIPI, VCC and DGM, it not only takes advantage of the advantages of Wave-CAIPI and VCC to reduce the number of system conditions, but the g-factor suitable for reconstruction is smaller and more uniform, so that the reconstructed graph has more High signal-to-noise ratio, and no need to collect ACS lines to estimate CSM or kernel in the process of solving, thus greatly shortening the data collection time in traditional convolutional neural networks that requires a large amount of training data to train network parameters, and avoids data collection. Accurate and introduced errors do not require time-consuming estimation of CSM or kernel in traditional reconstruction, which can be more suitable for clinical needs.

In some embodiments, before introducing the deep generative network model in the magnetic resonance reconstruction model of the Wave-CAIPI gradient encoding field in the present application, the method further includes: using parallel imaging to acquire a plurality of channels corresponding to different channels in the accelerated magnetic resonance imaging The undersampled k-space of , obtains an artifact-free image of the reconstructed undersampled k-space based on different coil sensitivity information.

Specifically, in accelerated magnetic resonance imaging, parallel imaging is an effective means of accelerated imaging to reduce the geometric factor, which simultaneously acquires multiple undersampled k-spaces corresponding to different channels, and the coil sensitivity distribution of each channel is Different, so there is a difference in coil sensitivity encoding between each k-space, that is, there is complementary information. By using different coil sensitivity information, an artifact-free image can be reconstructed from multiple undersampled k-spaces. , In essence, parallel imaging mainly uses redundant information (prior information) between different coil k spaces to achieve the purpose of undersampling to accelerate acquisition. The signal model is as follows,

(2)其中，g_y(t)和g_z(t)是在读出期间一对相位差π/2的Wave－CAIPI梯度场。in,

(2) where g _y (t) and g _z (t) are a pair of Wave-CAIPI gradient fields with a phase difference of π/2 during readout.

M表示在相位编码方向由可控混叠并行成像采样模式导致的偏移混叠，F_x表示在x方向的傅里叶变换，S表示线圈敏感度信息，Psf(k_x,y,z)为Wave－CAIPI梯度场的作用效果；通过wave(x,y,z)＝Em(x,y,z)和

得到

其中，Psf[x,y,z]为Psf(k_x,y,z)在读出方向的反傅里叶变换。In some embodiments, the introduction of a deep generative network model in the magnetic resonance reconstruction model of the Wave-CAIPI gradient encoding field in this application to accelerate magnetic resonance imaging includes: establishing an encoding model of the Wave-CAIPI gradient field in the magnetic resonance imaging: wave(x,y,z)=Em(x,y,z), where E is the encoding matrix,

M represents the offset aliasing caused by controllable aliasing parallel imaging sampling mode in the phase encoding direction, F _x represents the Fourier transform in the x direction, S represents the coil sensitivity information, Psf(k _x ,y,z) is the effect of the Wave-CAIPI gradient field; through wave(x,y,z)=Em(x,y,z) and

get

Among them, Psf[x,y,z] is the inverse Fourier transform of Psf(k _x ,y,z) in the readout direction.

其中S表示CSM，F_x表示在x方向的傅里叶变换，M表示在相位编码方向由CAIPIRINHA采样模式导致的偏移混叠。实际上，公式(3)和(4)可以等价写成，

其中Psf[x,y,z]是在Psf(k_x,y,z)是在读出方向的反傅里叶变换。通过在编码矩阵中引入Wave－CAIPI空间编码梯度，并且结合CAIPIRINHA，可以使得像素在3D空间中产生移动(混叠)，进而降低求解系统条件数，缩小几何因子(g－factor)。Specifically, in MRI, the effect of the Wave-CAIPI gradient field can be represented by Psf, which is a three-dimensional phase map with periodic sinusoidal variation, in which t and the encoding k _x of the k-space readout direction are in a one-to-one linear correspondence, Psf(t,y,z) can also be written as discrete form Psf(k _x ,y,z), and the Fourier transform of Psf(k _x ,y,z) in the y and z directions becomes Psf(k _x ,k _y ,k _z ), which can describe the offset of the Wave-CAIPI trajectory relative to the Cartesian trajectory, and inverse Fourier transform Psf(k _x ,y,z) in the readout direction, that is, it becomes Psf (x, y, z), which can describe the diffusion effect of the Wave-CAIPI gradient field in the readout direction. The coding model of Wave-CAIPI can be simplified as, wave(x,y,z)=Em(x,y,z)(3), where E is the coding matrix,

where S denotes the CSM, Fx denotes the Fourier transform in the _x direction, and M denotes the offset aliasing caused by the CAIPIRINHA sampling pattern in the phase encoding direction. In fact, equations (3) and (4) can be equivalently written as,

where Psf[x,y,z] is the inverse Fourier transform at Psf( _kx ,y,z) in the readout direction. By introducing the Wave-CAIPI spatial coding gradient into the coding matrix and combining with CAIPIRINHA, the pixels can be moved (aliased) in the 3D space, thereby reducing the condition number of the solution system and reducing the geometric factor (g-factor).

得到

其中，wave^*(x,y,z)表示通过VCC扩展后的数据，

表示在现有的PSf[x,y,z]基础上扩展通道数的Psf。In some embodiments, in the present application, the VCC is used to perform conjugate symmetry on the physical coil channel data to generate the VCC channel data, including: wave(x, y, z)=Em(x, y, z) and

get

Among them, wave ^* (x,y,z) represents the data expanded by VCC,

Represents a Psf that extends the number of channels based on the existing PSf[x, y, z].

(6)其中，wave^*(x,y,z)表示通过VCC扩展后的数据，

表示在原来的Psf[x,y,z]基础上扩展通道数的Psf。Specifically, using Wave-CIAPI to accelerate MRI imaging can effectively reduce g-factor and improve SNR. VCC (VCC) technology is another parallel imaging method to improve the system condition number of coding operators, in which VCC mainly uses the target The background phase and coil phase provide additional encoding capabilities. The specific method is to generate virtual conjugate coil channel data by conjugate symmetry to the data of the physical coil channel, and combine the two for reconstruction, which can further Reduce the number of conditions of the system, reduce the geometric factor, and improve the image SNR. After introducing the VCC technology in Wave-CAIPI, and combining (3) and (4), it can be obtained,

(6) Among them, wave ^* (x, y, z) represents the data expanded by VCC,

Indicates the Psf that expands the number of channels based on the original Psf[x,y,z].

得到经过VCC扩展后的几何因子g－factor，其中，

表示经过VCC扩展后的编码矩阵。In some embodiments, the reconstruction of the geometric factor calculation model by combining the physical coil channel data and the VCC channel data in this application includes: using the formula

The geometric factor g-factor after VCC expansion is obtained, where,

Indicates the encoding matrix after VCC expansion.

其中，

表示经过VCC扩展后的编码矩阵，(7)表示经过VCC扩展后的g－factor计算模型，原始g－factor的计算方式和(7)类似，只是E是没有经过VCC扩展后的模型。通过比较传统的g－factor和

可以得到经过VCC扩展后的模型会对g－factor有效的降低，提高图像重建的信噪比。Specifically, the g-factor after VCC expansion is obtained through (5) as follows:

in,

Represents the encoding matrix after VCC expansion, (7) represents the g-factor calculation model after VCC expansion, the original g-factor calculation method is similar to (7), but E is the model without VCC expansion. By comparing the traditional g-factor and

It can be obtained that the model after VCC expansion will effectively reduce the g-factor and improve the signal-to-noise ratio of image reconstruction.

In some embodiments, after generating the VCC channel data in the present application, the method further includes: introducing a deep generative model that does not require training.

Specifically, in the solution model in (6), the solution method based on the image domain is dominant. While using the advantages of Wave-CAIPI, it is still necessary to estimate the CSM or the kernel (data completion method in k-space) , it takes a certain amount of time to collect ACS in clinical practice, and it is estimated that CSM or kernel also needs a lot of time. In the present invention, a deep generative model (DGM) that does not require training is introduced while retaining the advantages of Wave-CAIPI. Combining equations (1), (3) and (4), the model proposed by the present invention is named as Wave-VCC-DGM,

Among them, G(ξ) represents DGM, ξ represents fixed random noise, and the output result after G(ξ) operation is the image to be solved. The core idea is to use the network parameters of DGM to fit the image to be solved. DGM It is a simple convolution generator (of course, it is not limited to the DGM network architecture in the present invention, DGM is only a model suitable for the image domain, if it is solved in k-space, the model needs to be changed to a network that conforms to the k-space solution. structure), which consists of Upsampling, Convolution-like, Batch Normalization (BN), and activation function layers. The structure is shown in Figure 4.

The deep generative network model used in the present invention itself can make an effective approximation to the traditional image domain-based CSM or k-space kernel, and contains all the previous assumptions. The model itself is low-parameterized and does not involve convolution, and has a simple structure. Although DMG does not use convolution operations, its structure is closely related to convolutional neural networks. Specifically, the network combines pixels between different channels. Since the coupling between pixels arranged in a linear manner is not provided, Therefore DGM is not a convolution operation in the traditional sense, but similar to the convolution operation in convolutional neural networks, the weights are shared between spatial locations. The coupling between pixels in the DMG originates from upsampling. It can be seen in (8) that the present invention combines DGM, Wave-CAIPI and VCC, and proposes a new network model Wave-VCC-DGM that does not require training, which can not only utilize the reduction system of Wave-CAIPI The advantage of the condition number, and the advantage of the VCC combined with the target background phase is used to further reduce the g-factor of the reconstructed image and improve the SNR of the image.

In addition, DGM can use the advantage of not requiring training, and directly use ADAM (not limited to ADAM) to solve the problem directly to meet the requirements of final image fitting, which can greatly reduce the cost of collecting training data in clinical practice. time, and does not need to consume a lot of time for CSM estimation or kernel calculation, which is very friendly for fast clinical implementation. The Wave-VCC-DGM model can make parallel imaging more flexible. In the traditional two types of methods for solving parallel imaging (based on k-space and based on image domain), the complexity of the solution process will increase, such as k-space-based calculation. For the kernel and the estimated CSM based on the image domain, it is relatively complicated to calculate the kernel in the non-Cartesian coordinate system (Non-Cartesian), but the model proposed in the present invention can avoid this problem because the present invention uses the Calibration-free method To solve, greatly reduce the complexity of the solution process.

The present invention has been proved by experiments that Wave-VCC has better effects. First, the simulated Wave coding (Psf is simulation) is used. The reconstruction results of , combined with Wave-CAIPI and VCC have better results. The data is sampled uniformly to achieve a 4x speedup.

In Figure 5, the simulated Wave coding model is used for preliminary experiments, and the traditional image domain-based reconstruction (taking SENSE as an example) is used. VCC) combined results with better reconstructed signal-to-noise ratio. The present invention also conducts a reconstruction test of the data encoded by the real Wave space. The amplitude of the Wave encoding is 1.2mT/m, and the number of cycles is 7. This is just an example, and the Wave is not limited to the above parameters. The results are shown in Figure 6. , the results show that WV-DGM has better effect than traditional WV-SENSE.

Further, referring to FIG. 2 , FIG. 2 shows an exemplary structural block diagram of a magnetic resonance imaging apparatus 200 based on a Wave gradient coding field and a deep learning model according to an embodiment of the present application.

As shown in Figure 2, the device includes:

The introduction unit 210 is used for introducing a deep generative network model into the magnetic resonance reconstruction model of the Wave-CAIPI gradient coding field to speed up the magnetic resonance imaging;

The generating unit 220 is configured to perform conjugate symmetry on the physical coil channel data through VCC to generate VCC channel data;

The reconstruction unit 230 is configured to combine the physical coil channel data and the VCC channel data to reconstruct the geometric factor calculation model.

It should be understood that the units or modules described in the apparatus 200 correspond to the respective steps in the method described with reference to FIG. 1 . Therefore, the operations and features described above with respect to the method are also applicable to the apparatus 200 and the units included therein, and details are not repeated here. The apparatus 200 may be pre-implemented in the browser of the electronic device or other security applications, or may be loaded into the browser of the electronic device or its security application by means of downloading or the like. Corresponding units in the apparatus 200 may cooperate with units in the electronic device to implement the solutions of the embodiments of the present application.

Referring to FIG. 3 below, it shows a schematic structural diagram of a computer system 300 suitable for implementing a terminal device or a server according to an embodiment of the present application.

As shown in FIG. 3, a computer system 300 includes a central processing unit (CPU) 301, which can be loaded into a random access memory (RAM) 303 according to a program stored in a read only memory (ROM) 302 or a program from a storage section 308 Instead, various appropriate actions and processes are performed. In the RAM 303, various programs and data necessary for the operation of the system 300 are also stored. The CPU 301 , the ROM 302 , and the RAM 303 are connected to each other through a bus 304 . An input/output (I/O) interface 305 is also connected to bus 304 .

The following components are connected to the I/O interface 305: an input section 306 including a keyboard, a mouse, etc.; an output section 307 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 308 including a hard disk, etc. ; and a communication section 309 including a network interface card such as a LAN card, a modem, and the like. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I/O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is mounted on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

In particular, according to an embodiment of the present disclosure, the process described above with reference to FIG. 1 may be implemented as a computer software program. For example, embodiments of the present disclosure include a method of magnetic resonance imaging based on a Wave-CAIPI gradient coded field and a deep learning model, comprising a computer program tangibly embodied on a machine-readable medium, the computer program comprising for executing Program code for the method of FIG. 1 . In such an embodiment, the computer program may be downloaded and installed from the network via the communication portion 309 and/or installed from the removable medium 311 .

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more functions for implementing the specified logical function(s) executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented in dedicated hardware-based systems that perform the specified functions or operations , or can be implemented in a combination of dedicated hardware and computer instructions.

The units or modules involved in the embodiments of the present application may be implemented in a software manner, and may also be implemented in a hardware manner. The described unit or module may also be provided in the processor, for example, it may be described as: a processor includes a first sub-area generating unit, a second sub-area generating unit and a display area generating unit. Wherein, the names of these units or modules do not constitute a limitation on the units or modules themselves, for example, the display area generating unit may also be described as "used to generate unit of the display area of the text".

As another aspect, the present application also provides a computer-readable storage medium, and the computer-readable storage medium may be the computer-readable storage medium included in the aforementioned apparatus in the foregoing embodiment; computer-readable storage medium in the device. The computer-readable storage medium stores one or more programs used by one or more processors to execute the text generation method described in this application for a transparent window envelope.

The above description is only a preferred embodiment of the present application and an illustration of the applied technical principles. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to the technical solution formed by the specific combination of the above-mentioned technical features, and should also cover the above-mentioned technical features or Other technical solutions formed by any combination of its equivalent features. For example, a technical solution is formed by replacing the above-mentioned features with the technical features disclosed in this application (but not limited to) with similar functions.

Claims (10)

1. A magnetic resonance imaging method based on a wave gradient coding field and a deep learning model, which is characterized by comprising the following steps:

introducing a depth generation network model into a magnetic resonance reconstruction model of the wave gradient coding field to accelerate magnetic resonance imaging;

conjugate symmetry is carried out on the physical coil channel data through a virtual conjugate coil to generate virtual conjugate coil channel data;

and merging the physical coil channel data and the virtual conjugate coil channel data to reconstruct a geometric factor calculation model.

2. The method of claim 1, wherein before introducing the depth generation network model into the wave gradient encoding field based magnetic resonance reconstruction model, the method further comprises:

a plurality of undersampled k-spaces corresponding to different channels are acquired in magnetic resonance accelerated imaging using parallel imaging,

the reconstructed artifact-free images of the undersampled k-space are obtained on the basis of different coil sensitivity information.

3. The method according to claim 2, wherein the step of introducing a depth generation network model into the magnetic resonance reconstruction model of the wave gradient coding field to accelerate magnetic resonance imaging comprises:

establishing an encoding model of a wave gradient field in magnetic resonance imaging: wave (x, y, z) ═ Em (x, y, z), where E is the coding matrix,

m represents the offset aliasing in the phase encoding direction caused by the controlled aliasing parallel imaging sampling mode, F_xDenotes the Fourier transform in the x-direction, S denotes coil sensitivity information, Psf (k)_xY, z) is the effect of the wave gradient field;

by wave (x, y, z) ═ Em (x, y, z) and

to obtain

Wherein Psf [ x, y, z]Is Psf (k)_xY, z) in the readout direction.

4. The magnetic resonance imaging method based on the wave gradient coding field and the deep learning model as claimed in claim 3, wherein the generating of the virtual conjugate coil channel data by conjugate symmetry of the virtual conjugate coil to the physical coil channel data comprises:

by wave (x, y, z) ═ Em (x, y, z) and

to obtain

Wherein, wave^*(x, y, z) represents data expanded by a virtual conjugate coil,

is shown in the existing Psf [ x, y, z ]]And expanding the Psf of the number of channels on the basis.

5. The method of claim 4, wherein after generating the virtual conjugate coil channel data, the method further comprises:

deep generative models without training are introduced.

6. The method of claim 4, wherein the combining of the physical coil channel data and the virtual conjugate coil channel data to reconstruct the geometric factor calculation model comprises:

by the formula

Obtaining the geometric factor g-factor after VCC expansion, wherein,

representing the coding matrix after VCC spreading.

7. A magnetic resonance imaging apparatus based on a wave gradient encoding field and a deep learning model, the apparatus comprising:

the introduction unit is used for introducing a depth generation network model into a magnetic resonance reconstruction model of the wave gradient coding field to accelerate magnetic resonance imaging;

the generating unit is used for carrying out conjugate symmetry on the physical coil channel data through the virtual conjugate coil to generate virtual conjugate coil channel data;

and the reconstruction unit is used for combining the physical coil channel data and the virtual conjugate coil channel data to reconstruct a geometric factor calculation model.

8. The apparatus according to claim 7, wherein before introducing the depth generation network model into the magnetic resonance reconstruction model of the wave gradient encoding field, the apparatus further comprises:

a plurality of undersampled k-spaces corresponding to different channels are acquired in magnetic resonance accelerated imaging using parallel imaging,

the reconstructed artifact-free images of the undersampled k-space are obtained on the basis of different coil sensitivity information.

9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1-6 when executing the program.

10. A computer-readable storage medium having stored thereon a computer program for:

the computer program, when executed by a processor, implementing the method as claimed in any one of claims 1-6.

Images