Magnetic Resonance Imaging Method, Device, Computer Equipment and Storage Medium

Abstract

The present application relates to a magnetic resonance imaging method, apparatus, computer device, and storage medium. The method includes: performing multiple excitations on a scanning object and acquiring multiple sets of diffusion-weighted echo signals, with each set of diffusion-weighted echo signals corresponding to one excitation; obtaining the phase information of each set of diffusion-weighted echo signals; correcting the phase information of each set of diffusion-weighted echo signals to obtain the corrected phase information of each set of diffusion-weighted echo signals; and performing image reconstruction based on each diffusion-weighted echo signal and the corrected phase information of each set of diffusion-weighted echo signals to obtain a magnetic resonance diffusion-weighted image. Using this method can improve the quality of the obtained magnetic resonance diffusion-weighted image.

Description

Technical Field

[0001] This application relates to the field of magnetic resonance imaging technology, and in particular, to a magnetic resonance imaging method, apparatus, computer device, and storage medium. Background Art

[0002] With the development of magnetic resonance imaging technology, magnetic resonance diffusion imaging methods have emerged. Magnetic resonance diffusion imaging is currently the only non-invasive method that can measure the diffusion movement of water molecules in tissues and image them in vivo. It detects the microscopic structure of tissues by measuring and quantifying the diffusion information of water molecules in the tissues.

[0003] In traditional technologies, magnetic resonance diffusion weighted imaging mainly uses single-shot echo planar imaging, and image reconstruction is performed based on the acquired magnetic resonance data and the obtained echo data to obtain a magnetic resonance diffusion weighted image.

[0004] However, the imaging method of traditional magnetic resonance diffusion weighted images has the problem of poor image quality. Summary of the Invention

[0005] Based on this, in view of the above technical problems, it is necessary to provide a magnetic resonance imaging method, apparatus, computer device, and storage medium that can improve the quality of the obtained magnetic resonance diffusion weighted image.

[0006] A magnetic resonance imaging method, the method includes:

[0007] Performing multiple excitations on a scanning object and collecting multiple sets of diffusion weighted echo signals, each set of diffusion weighted echo signals corresponding to one excitation;

[0008] Obtaining the phase information of each set of diffusion weighted echo signals;

[0009] Correcting the phase information of each set of diffusion weighted echo signals to obtain the corrected phase information of each set of diffusion weighted echo signals;

[0010] Performing image reconstruction based on each of the diffusion weighted echo signals and the corrected phase information of each set of diffusion weighted echo signals to obtain a magnetic resonance diffusion weighted image.

[0011] In one embodiment, the performing image reconstruction based on each of the diffusion weighted echo signals and the corrected phase information of each set of diffusion weighted echo signals to obtain a magnetic resonance diffusion weighted image includes:

[0012] Filling each of the diffusion weighted echo signals into the same K-space to obtain K-space data;

[0013] Obtaining the magnetic resonance diffusion weighted image based on the K-space data and the corrected phase information of each set of diffusion weighted echo signals.

[0014] In one embodiment, before reconstructing an image based on the phase information corrected according to each of the diffusion-weighted echo signals and each group of diffusion-weighted echo signals to obtain a magnetic resonance diffusion-weighted image, the method further includes:

[0015] Obtaining a physiological motion curve of the scanned object;

[0016] Determining a weighting value for each group of diffusion-weighted echo signals according to the physiological motion curve, where the weighting value represents the filling proportion of each group of diffusion-weighted echo signals in the K-space.

[0017] In one embodiment, the phase information corrected for each group of diffusion-weighted echo signals is obtained by the following method:

[0018] Inputting each group of diffusion-weighted echo signals or the phase information of each group of diffusion-weighted echo signals into a preset neural network model to obtain the phase information corrected for each group of diffusion-weighted echo signals.

[0019] In one embodiment, the phase information of each group of diffusion-weighted echo signals is obtained by the following method:

[0020] Performing a navigation sequence after each excitation of the scanned object and collecting navigation signals;

[0021] Obtaining the phase information of each group of diffusion-weighted echo signals according to the navigation signals.

[0022] In one embodiment, the acquisition timing sequence for acquiring each group of diffusion-weighted echo signals includes a bipolar gradient timing sequence or a unipolar gradient timing sequence.

[0023] In one embodiment, each group of diffusion-weighted echo signals corresponds to different phase encoding positions in the K-space.

[0024] A magnetic resonance imaging device, the device includes:

[0025] An acquisition module, configured to perform multiple excitations on a scanned object and acquire multiple groups of diffusion-weighted echo signals, where each group of diffusion-weighted echo signals corresponds to one excitation;

[0026] A first acquisition module, configured to acquire the phase information of each group of diffusion-weighted echo signals;

[0027] A correction module, configured to correct the phase information of each group of diffusion-weighted echo signals to obtain the phase information corrected for each group of diffusion-weighted echo signals;

[0028] A reconstruction module, configured to perform image reconstruction based on each of the diffusion-weighted echo signals and the phase information after correction of each group of diffusion-weighted echo signals, so as to obtain a magnetic resonance diffusion-weighted image.

[0029] A computer device includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the following steps are implemented:

[0030] Perform multiple excitations on a scanning object and collect multiple groups of diffusion-weighted echo signals, where each group of diffusion-weighted echo signals corresponds to one excitation;

[0031] Obtain the phase information of each group of diffusion-weighted echo signals;

[0032] Correct the phase information of each group of diffusion-weighted echo signals to obtain the phase information after correction of each group of diffusion-weighted echo signals;

[0033] Perform image reconstruction based on each of the diffusion-weighted echo signals and the phase information after correction of each group of diffusion-weighted echo signals, so as to obtain a magnetic resonance diffusion-weighted image.

[0034] A computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the following steps are implemented:

[0035] Perform multiple excitations on a scanning object and collect multiple groups of diffusion-weighted echo signals, where each group of diffusion-weighted echo signals corresponds to one excitation;

[0036] Obtain the phase information of each group of diffusion-weighted echo signals;

[0037] Correct the phase information of each group of diffusion-weighted echo signals to obtain the phase information after correction of each group of diffusion-weighted echo signals;

[0038] Perform image reconstruction based on each of the diffusion-weighted echo signals and the phase information after correction of each group of diffusion-weighted echo signals, so as to obtain a magnetic resonance diffusion-weighted image.

[0039] The above-mentioned magnetic resonance imaging method, device, computer device, and storage medium can collect a set of diffusion-weighted echo signals corresponding to each excitation by performing multiple excitations on the scanned object, obtain the phase information of each set of diffusion-weighted echo signals, and at the same time correct the phase information of each set of diffusion-weighted echo signals, so as to obtain the corrected phase information of each set of diffusion-weighted echo signals. Furthermore, image reconstruction can be performed based on the diffusion-weighted echo signals corresponding to each excitation and the corrected phase information to obtain a magnetic resonance diffusion-weighted image. Since the obtained magnetic resonance diffusion-weighted image is obtained by image reconstruction based on the diffusion-weighted echo signals corresponding to each excitation and the corrected phase information, and the corrected phase information corresponding to each excitation is a correction of the phase information corresponding to each excitation, it ensures that the phases between different excitations can be kept consistent, thereby reducing the defects of artifacts, blurring, and distortion in the obtained magnetic resonance diffusion-weighted image and improving the quality of the obtained magnetic resonance diffusion-weighted image. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 is a schematic internal structure diagram of a magnetic resonance imaging device in an embodiment;

[0041] Figure 2 is a schematic flowchart of a magnetic resonance imaging method in an embodiment;

[0042] Figure 2a is a schematic diagram of the bipolar gradient timing with navigation echoes in an embodiment;

[0043] Figure 2b is a schematic diagram of the bipolar gradient timing without navigation echoes in an embodiment;

[0044] Figure 2c is a schematic diagram of the unipolar gradient timing with navigation echoes in an embodiment;

[0045] Figure 2d is a schematic diagram of the unipolar gradient timing without navigation echoes in an embodiment;

[0046] Figure 3 is a schematic flowchart of a magnetic resonance imaging method in an embodiment;

[0047] Figure 3a is a schematic diagram of filling each set of diffusion-weighted echo signals into the same k-space in an embodiment;

[0048] Figure 4 is a schematic flowchart of a magnetic resonance imaging method in an embodiment;

[0049] Figure 4a is a schematic diagram of a magnetic resonance diffusion-weighted image obtained by using traditional single-shot echo planar imaging diffusion imaging in an embodiment;

[0050] Figure 4b Schematic diagram of a magnetic resonance diffusion weighted image obtained in an embodiment;

[0051] Figure 5 Schematic flow chart of a magnetic resonance imaging method in an embodiment;

[0052] Figure 6 Block diagram of the structure of a magnetic resonance imaging apparatus in an embodiment;

[0053] Figure 7 Internal structure diagram of a computer device in an embodiment. Specific embodiments

[0054] In order to make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0055] The magnetic resonance imaging method provided by the embodiments of the present application can be applicable to a magnetic resonance imaging device as shown in Figure 1 The magnetic resonance imaging device includes a processor and a memory connected by a system bus. A computer program is stored in the memory. When the processor executes the computer program, it can execute the steps of the following method embodiments. Optionally, the magnetic resonance imaging device may further include a network interface, a display screen, and an input device. Among them, the processor of the magnetic resonance imaging device is used to provide computing and control capabilities. The memory of the magnetic resonance imaging device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the magnetic resonance imaging device is used to communicate with an external terminal through a network connection. The specific form of the magnetic resonance imaging device in the embodiments of the present application is not limited.

[0056] In one embodiment, as shown in Figure 2 A magnetic resonance imaging method is provided. Taking the method applied to the magnetic resonance imaging device in Figure 1 as an example, the method includes the following steps:

[0057] S201, perform multiple excitations on a scanning object and collect multiple sets of diffusion weighted echo signals, and each set of diffusion weighted echo signals corresponds to one excitation.

[0058] Among them, the excitation of magnetic resonance refers to emitting a pulse sequence to the scanned object. The pulse sequence may include radio frequency pulses, slice selection gradient fields, phase encoding gradient fields, frequency encoding gradient fields, etc. The setting of various parameters related to radio frequency pulses, gradient fields, signal acquisition times, etc. and their arrangement in time sequence is the pulse sequence. In this embodiment, the nuclear spins in the scanned object are excited by emitting an echo planar imaging (EPI) pulse sequence, and then the diffusion weighted echo signal corresponding to this excitation is obtained by using an echo sequence. Specifically, the magnetic resonance imaging device performs multiple excitations on the scanned object and acquires the diffusion weighted echo signal corresponding to each excitation. Optionally, the magnetic resonance imaging device may use a pulse sequence and a subsequent applied navigation sequence to acquire the diffusion weighted echo signal and the navigation signal corresponding to each excitation. Optionally, the acquisition time sequence for the magnetic resonance imaging device to acquire the diffusion weighted echo signal corresponding to each excitation includes a bipolar gradient time sequence or a unipolar gradient time sequence. It should be noted here that the bipolar gradient time sequence includes a bipolar gradient time sequence with a navigation echo (such as Figure 2a shown) and a bipolar gradient time sequence without a navigation echo (such as Figure 2b shown), and the unipolar gradient time sequence also includes a unipolar gradient time sequence with a navigation echo (such as Figure 2c shown) and a unipolar gradient time sequence without a navigation echo (such as Figure 2d shown). Generally, the bipolar gradient time sequence with a navigation echo can provide the phase information corresponding to each excitation, but the navigation echo will increase the acquisition time. For the bipolar gradient time sequence without a navigation echo, the phase information corresponding to each excitation can be obtained from the K-space data acquired by each excitation.

[0059] For the bipolar gradient time sequence with a navigation echo, as Figure 2a shown, first a 90° excitation pulse is applied, and then a 180° refocusing pulse is applied; (while the two pulses are applied, a slice selection gradient is applied in the slice selection gradient Gss direction), diffusion gradients (the gray areas in the figure) are applied before and after the 180° pulse; after the diffusion gradient is applied, a pre-gradient is first applied, and then a time-continuous reversed readout gradient 601; a spike pulse gradient 602 is applied at the end of the inversion period of the readout gradient; after applying the second 180° refocusing pulse, a navigation sequence is applied.

[0060] For the bipolar gradient time sequence without a navigation echo, as Figure 2b shown, first a 90° excitation pulse is applied, and then a 180° refocusing pulse is applied; (while the two pulses are applied, a slice selection gradient is applied in the slice selection gradient Gss direction) diffusion gradients (the gray areas in the figure) are applied before and after the 180° pulse; after the diffusion gradient is applied, a pre-gradient is first applied, and then a time-continuous reversed readout gradient 701; a spike pulse gradient 702 is applied during the readout gradient polarity inversion interval.

[0061] For a unipolar gradient timing with navigator echoes, such as Figure 2c shown, first apply a 90° excitation pulse, and then apply a 180° refocusing pulse; (while applying the two pulses, apply a slice selection gradient in the direction of the slice selection gradient Gss), apply a diffusion gradient (the gray area in the figure) before and after the 180° pulse; apply a navigator sequence after applying the second 180° refocusing pulse.

[0062] For a unipolar gradient timing without navigator echoes, such as Figure 2d shown, first apply a 90° excitation pulse, and then a 180° refocusing pulse at time; (while applying the two pulses, apply a slice selection gradient in the direction of the slice selection gradient Gss); apply a diffusion gradient (the gray area in the figure) before and after the 180° pulse; first apply a pre-gradient after applying the diffusion gradient, and then a continuously reversed readout gradient 901 at time; apply a spike pulse gradient 902 at the end of the inversion period of the readout gradient; 903 and 904 are similar to the foregoing description. It should be noted that traditional echo-planar diffusion-weighted imaging obtains all the K-space data by single-shot excitation, while in the embodiments of the present application, all the data in the K-space is obtained by multiple excitations of the scanned object. Optionally, the phase information of each excitation is recorded using navigator echo data or the K-space data obtained in the nth time after each excitation. Optionally, the number of times of multiple excitations of the scanned object is at least two.

[0063] S202, obtain the phase information of each group of diffusion-weighted echo signals.

[0064] Specifically, the magnetic resonance imaging device obtains the phase information of each group of diffusion-weighted echo signals while acquiring the diffusion-weighted echo signals corresponding to each excitation. Optionally, the phase information of each group of diffusion-weighted echo signals may be the same or different. Optionally, the magnetic resonance imaging device may obtain the phase information of each group of diffusion-weighted echo signals according to the navigator sequence corresponding to each excitation.

[0065] S203, correct the phase information of each group of diffusion-weighted echo signals to obtain the corrected phase information of each group of diffusion-weighted echo signals.

[0066] Specifically, the magnetic resonance imaging device corrects the phase information of each group of diffusion-weighted echo signals to obtain the corrected phase information of each group of diffusion-weighted echo signals. Optionally, the magnetic resonance imaging device may input the phase information of each group of diffusion-weighted echo signals into a preset correction model to correct the phase information of each group of diffusion-weighted echo signals, or correct the phase information of each group of diffusion-weighted echo signals according to a correction algorithm to obtain the corrected phase information of each group of diffusion-weighted echo signals.

[0067] S204. Image reconstruction is performed based on each diffusion-weighted echo signal and the phase information corrected for each group of diffusion-weighted echo signals to obtain a magnetic resonance diffusion-weighted image.

[0068] Specifically, the magnetic resonance imaging device performs image reconstruction based on each of the above-mentioned diffusion-weighted echo signals (the multiple groups of diffusion-weighted echo signals described in S201 above) and the phase information corrected for each group of diffusion-weighted echo signals to obtain a magnetic resonance diffusion-weighted image. Optionally, the magnetic resonance imaging device may perform reconstruction on each of the above-mentioned diffusion-weighted echo signals and the phase information corrected for each group of diffusion-weighted echo signals using an image reconstruction algorithm. Optionally, the image reconstruction algorithm includes, but is not limited to, an iterative algorithm with a penalty term.

[0069] In the above-mentioned magnetic resonance imaging method, by performing multiple excitations on the scanned object, a group of diffusion-weighted echo signals corresponding to each excitation can be collected, and the phase information of each group of diffusion-weighted echo signals can be obtained. At the same time, by correcting the phase information of each group of diffusion-weighted echo signals, the phase information corrected for each group of diffusion-weighted echo signals can be obtained. Furthermore, image reconstruction can be performed based on the diffusion-weighted echo signals corresponding to each excitation and the corrected phase information to obtain a magnetic resonance diffusion-weighted image. Since the obtained magnetic resonance diffusion-weighted image is obtained by performing image reconstruction based on the diffusion-weighted echo signals corresponding to each excitation and the corrected phase information, and the corrected phase information corresponding to each excitation is a correction of the phase information corresponding to each excitation, it ensures that the phases between different excitations can be kept consistent, thereby reducing the artifacts, blurring, and deformation defects of the obtained magnetic resonance diffusion-weighted image and improving the quality of the obtained magnetic resonance diffusion-weighted image.

[0070] In the scenario of performing image reconstruction based on each diffusion-weighted echo signal and the phase information corrected for each group of diffusion-weighted echo signals to obtain a magnetic resonance diffusion-weighted image, in one embodiment, as Figure 3 shown, the above S303 includes:

[0071] S301. Fill each diffusion-weighted echo signal into the same K-space to obtain K-space data.

[0072] Specifically, the magnetic resonance imaging device fills the diffusion-weighted echo signals corresponding to each of the above-mentioned excitations into the same K-space to obtain K-space data. Optionally, each group of diffusion-weighted echo signals corresponds to different phase encoding positions in the above-mentioned K-space. Optionally, the magnetic resonance imaging device may fill the diffusion-weighted echo signals corresponding to the same excitation into the same row or the same column of the K-space to obtain K-space data. Optionally, in one embodiment, the scanned object is excited four times, and four groups of diffusion-weighted echo signals of magnetic resonance imaging data corresponding to each excitation are collected; the filling of each group of diffusion-weighted echo signals in the K-space is asFigure 3a As shown; in this embodiment, four sets of diffusion-weighted echo signals are filled into the same k-space, and the k-space is divided into multiple regions, and each region is filled with diffusion-weighted echo signals collected by different excitations; for the diffusion-weighted echo signals collected by different excitations filled in the same region, the filling directions of the encoding data lines are the same; in this embodiment, through the above solution, the phase difference of the encoding data lines of the magnetic resonance signals collected by different excitations can be reduced; and the motion artifacts caused by the movement of the detection object during different excitations can be reduced.

[0073] S302, obtaining the magnetic resonance diffusion-weighted image according to the k-space data and the phase information after correction of each group of diffusion-weighted echo signals.

[0074] Specifically, the magnetic resonance imaging device obtains the magnetic resonance diffusion-weighted image according to the obtained k-space data and the phase information after correction of each group of diffusion-weighted echo signals. Optionally, the magnetic resonance imaging device may perform image reconstruction on the obtained k-space data and the phase information after correction of each group of diffusion-weighted echo signals by using an image reconstruction algorithm to obtain the above-mentioned magnetic resonance diffusion-weighted image. Optionally, the image reconstruction algorithm includes, but is not limited to, an iterative algorithm with a penalty term.

[0075] In this embodiment, the process of filling the diffusion-weighted echo signals corresponding to each excitation into the same k-space by the magnetic resonance imaging device is relatively simple, and the k-space data can be obtained quickly. Furthermore, the magnetic resonance diffusion-weighted image can be obtained according to the obtained k-space data and the phase information after correction of the diffusion-weighted echo signals corresponding to each excitation. And the phase information after correction of each group of diffusion-weighted echo signals is the corrected phase information corresponding to each excitation, ensuring that the phases between different excitations can be kept consistent, thereby reducing the defects of artifacts, blurring, and deformation in the obtained magnetic resonance diffusion-weighted image and improving the quality of the obtained magnetic resonance diffusion-weighted image.

[0076] Before performing image reconstruction according to each diffusion-weighted echo signal and the phase information after correction of each group of diffusion-weighted echo signals to obtain the magnetic resonance diffusion-weighted image, a weighting value representing the filling ratio of each group of diffusion-weighted echo signals in the k-space can also be obtained first. In one embodiment, as Figure 4 shown, the above method further includes:

[0077] S401, obtaining the physiological motion curve of the scanned object.

[0078] Specifically, the magnetic resonance imaging device obtains the physiological motion curve of the scanned object. Optionally, the magnetic resonance imaging device may detect the physiological signals of the scanned object through a physiological signal detection device, and then generate the physiological motion curve of the scanned object according to the detected physiological signals.

[0079] S402. Determine the weighting values of each group of diffusion - weighted echo signals according to the physiological motion curve, where the weighting values represent the filling proportion of each group of diffusion - weighted echo signals in the K - space.

[0080] Specifically, the magnetic resonance imaging device determines the weighting values of each group of diffusion - weighted echo signals according to the obtained physiological motion curve of the scanned object. Among them, the weighting values of each group of diffusion - weighted echo signals represent the filling proportion of each group of diffusion - weighted echo signals in the above - mentioned K - space. Optionally, the magnetic resonance imaging device can determine the weighting values of each group of diffusion - weighted echo signals according to the amplitude of the physiological motion curve of the scanned object. Optionally, the magnetic resonance imaging device can determine the weighting values of each group of diffusion - weighted echo signals, the sensitivity information of the magnetic resonance coil, and the phase information of each group of diffusion - weighted echo signals after correction as reconstruction parameters, and then perform image reconstruction according to the following formula to obtain the above - mentioned magnetic resonance diffusion - weighted image: In the formula, represents the initial magnetic resonance diffusion - weighted image with severe artifacts and poor clarity, which is obtained by filling the K - space with diffusion - weighted echo signals collected multiple times and performing Fourier reconstruction in this embodiment; s0 represents the reconstructed magnetic resonance diffusion - weighted image; p n is the phase information of each group of diffusion - weighted echo signals after correction obtained by the above - mentioned preset neural network model; n represents the number of excitations; c represents the sensitivity information of the magnetic resonance coil. Optionally, the sensitivity information of the magnetic resonance coil can be the sensitivity matrix of the magnetic resonance coil; D n is the data selection matrix, which is used to represent which excitation the current excitation is; W n is the weighting value of each group of diffusion - weighted echo signals. Optionally, the weighting value of each group of diffusion - weighted echo signals is related to the magnetic resonance data of each excitation, and the weighting value of each group of diffusion - weighted echo signals can be determined by the magnetic resonance data of each excitation; F H and F are the inverse Fourier transform and Fourier transform operations respectively.

[0081] In one embodiment, the sensitivity information of the magnetic resonance coil can first collect multiple data lines in the K - space through the receiving coil, and obtain the corresponding calibration matrix through these multiple data lines; then, perform singular value decomposition on the calibration matrix to obtain the spatial vector composed of the eigenvectors with eigenvalue 1, which constitutes the coil sensitivity.

[0082] According to the above formula, taking the corrected phase information corresponding to each excitation and the magnetic resonance coil sensitivity information as known information, a high-quality image with high clarity, small artifacts, and small deformation can be solved from the currently poor-quality image. It should be noted that the essence of the above formula is matrix inversion. However, for high-dimensional matrices, the computational amount of traditional inverse matrix operations is huge. Therefore, the present application uses the nonlinear conjugate gradient method to iteratively solve the inverse matrix. By adopting this method, the computational amount can be greatly reduced. In addition, the present application adds an appropriate penalty term to the iterative solution algorithm to prevent overfitting of data. In addition, the reconstruction algorithm in the present application also introduces a data selection mechanism to eliminate and re-acquire poor-quality data. Exemplarily, as Figure 4a and Figure 4b shown Figure 4a Figure Figure 4a is a magnetic resonance diffusion-weighted image obtained by using traditional single-shot echo-planar diffusion imaging Figure 4b Figure Figure 4b is the magnetic resonance diffusion-weighted image obtained by the present application. It can be seen from Figure 4b that the magnetic resonance diffusion-weighted image obtained by the present application has the characteristics of small deformation and high image clarity

[0083] In this embodiment, the process of the magnetic resonance imaging device for obtaining the physiological motion curve of the scanned object is very simple, so that the magnetic resonance imaging device can quickly determine the weighting value representing the filling ratio of each group of diffusion-weighted echo signals in the K space according to the physiological motion curve of the scanned object, thereby improving the efficiency of obtaining the weighting values of each group of diffusion-weighted echo signals

[0084] In the above scenario of obtaining the phase information of each group of diffusion-weighted echo signals, in one embodiment, S203 includes: inputting each group of diffusion-weighted echo signals or the phase information of each group of diffusion-weighted echo signals into a preset neural network model to obtain the corrected phase information of each group of diffusion-weighted echo signals

[0085] Specifically, the magnetic resonance imaging device inputs each set of diffusion-weighted echo signals or the phase information of each set of diffusion-weighted echo signals into a preset neural network model, and obtains the phase information of the above-mentioned sets of diffusion-weighted echo signals after correction through the preset neural network model. It can be understood that the preset neural network model is a pre-trained neural network model. Optionally, the magnetic resonance imaging device can obtain the above neural network model through the following two training methods: Method 1: Collect a batch of fully sampled and phase-consistent k-space data, generate undersampled and phase-inconsistent k-space data from the fully sampled and phase-consistent k-space data, use the fully sampled and phase-consistent k-space data as the output, and the undersampled and phase-inconsistent k-space data as the input, and obtain the above neural network model through training; Method 2: Collect a batch of fully sampled and simultaneously phase-consistent navigator echo data; use the navigator echo data as the input of the neural network, and the fully sampled imaging data as the expected output, and obtain the above neural network model through training.

[0086] In this embodiment, the process of the magnetic resonance imaging device inputting each set of diffusion-weighted echo signals or the phase information of each set of diffusion-weighted echo signals into a preset neural network model and obtaining the phase information of each set of diffusion-weighted echo signals after correction through the neural network model is relatively simple, thereby improving the efficiency of obtaining the phase information of each set of diffusion-weighted echo signals after correction, and further improving the efficiency of obtaining magnetic resonance diffusion-weighted images.

[0087] In the scenario where the above magnetic resonance imaging device obtains the phase information of each set of diffusion-weighted echo signals, in one embodiment, as Figure 5 shown, the above S202 includes:

[0088] S501, execute a navigator sequence after each excitation of the scanned object, and collect navigator signals.

[0089] Specifically, the magnetic resonance imaging device executes a navigator sequence after each excitation of the scanned object and collects navigator signals. Optionally, the magnetic resonance imaging device can collect navigator signals according to the echo signals of the navigator sequence executed after each excitation. Optionally, if the acquisition timing of the diffusion-weighted echo signals corresponding to each excitation is a bipolar gradient timing with navigator echoes, the magnetic resonance imaging device can apply a navigator sequence after the second 180° refocusing pulse as Figure 2a shown, and collect navigator signals; if the acquisition timing of the diffusion-weighted echo signals corresponding to each excitation is a bipolar gradient timing without navigator echoes, the magnetic resonance imaging device can obtain navigator signals through the k-space data collected by each excitation; if the acquisition timing of the diffusion-weighted echo signals corresponding to each excitation is a unipolar gradient timing with navigator echoes, the magnetic resonance imaging device can be at Figure 2cAfter the second 180° refocusing pulse shown, a navigation sequence is applied to acquire navigation signals; if the acquisition timing of the diffusion-weighted echo signals corresponding to each excitation is a unipolar gradient timing without navigation echoes, the magnetic resonance imaging device can obtain navigation signals from the K-space data acquired for each excitation.

[0090] S502, obtaining the phase information of each set of diffusion-weighted echo signals according to the navigation signals.

[0091] Specifically, the magnetic resonance imaging device obtains the phase information of each set of diffusion-weighted echo signals according to the navigation signals acquired each time the navigation sequence is executed. Optionally, the magnetic resonance imaging device can analyze the navigation signals acquired each time the navigation sequence is executed to obtain the phase information of each set of diffusion-weighted echo signals.

[0092] In this embodiment, the process of the magnetic resonance imaging device executing the navigation sequence after each excitation of the scanned object is relatively simple, so that the navigation signals can be acquired quickly after the execution of the navigation sequence, and then the phase information of each set of diffusion-weighted echo signals can be obtained according to the navigation signals. Since the efficiency of acquiring the navigation signals is improved, the efficiency of obtaining the phase information of each set of diffusion-weighted echo signals according to the navigation signals is also improved.

[0093] It should be understood that although Figure 2-5 the steps in the flowchart of Figure 2-5 are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise clearly stated in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover,

[0094] In one embodiment, as Figure 6 shown, a magnetic resonance imaging device is provided, including: an acquisition module, a first acquisition module, a correction module, and a reconstruction module, where:

[0095] The acquisition module is configured to perform multiple excitations on the scanned object and acquire multiple sets of diffusion-weighted echo signals, and each set of diffusion-weighted echo signals corresponds to one excitation.

[0096] The first acquisition module is configured to acquire the phase information of each set of diffusion-weighted echo signals;

[0097] A correction module for correcting the phase information of each group of diffusion-weighted echo signals to obtain the corrected phase information of each group of diffusion-weighted echo signals.

[0098] A reconstruction module for performing image reconstruction based on each of the diffusion-weighted echo signals (i.e., multiple groups of diffusion-weighted echo signals) and the corrected phase information of each group of diffusion-weighted echo signals to obtain a magnetic resonance diffusion-weighted image.

[0099] Optionally, the acquisition timing for acquiring each group of diffusion-weighted echo signals includes bipolar gradient timing or unipolar gradient timing.

[0100] The magnetic resonance imaging device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effects are similar, which will not be elaborated here.

[0101] Based on the above embodiment, optionally, the above reconstruction module includes: a first acquisition unit and a reconstruction unit, where:

[0102] The first acquisition unit is used to fill each of the diffusion-weighted echo signals into the same K-space to obtain K-space data.

[0103] The reconstruction unit is used to obtain the magnetic resonance diffusion-weighted image based on the K-space data and the corrected phase information of each group of diffusion-weighted echo signals.

[0104] Optionally, each group of diffusion-weighted echo signals corresponds to different phase encoding positions in the K-space.

[0105] The magnetic resonance imaging device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effects are similar, which will not be elaborated here.

[0106] Based on the above embodiment, optionally, the above device further includes: a second acquisition module and a determination module, where:

[0107] The second acquisition module is used to acquire the physiological motion curve of the scanned object.

[0108] The third acquisition module is used to determine the weighting value of each group of diffusion-weighted echo signals according to the physiological motion curve, and the weighting value characterizes the filling proportion of each group of diffusion-weighted echo signals in the K-space.

[0109] The magnetic resonance imaging device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effects are similar, which will not be elaborated here.

[0110] Based on the above embodiment, optionally, the correction module includes: a second acquisition unit, where:

[0111] A second acquisition unit, configured to input the diffusion-weighted echo signal of each group or the phase information of the diffusion-weighted echo signal of each group into a preset neural network model, so as to obtain the corrected phase information of the diffusion-weighted echo signal of each group.

[0112] The magnetic resonance imaging device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here.

[0113] Based on the above embodiment, optionally, the above first acquisition module includes: an acquisition unit and a third acquisition unit, where:

[0114] The acquisition unit is configured to execute a navigation sequence after each excitation of the scanned object and acquire navigation signals.

[0115] The third acquisition unit is configured to obtain the phase information of the diffusion-weighted echo signal of each group according to the navigation signals.

[0116] The magnetic resonance imaging device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here.

[0117] For the specific definition of the magnetic resonance imaging device, reference can be made to the definition of the magnetic resonance imaging method in the above text, which will not be elaborated here. Each module in the above magnetic resonance imaging device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0118] In one embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 7As shown in the figure. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it realizes a magnetic resonance imaging method. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the casing of the computer device, or an external keyboard, a touchpad, or a mouse, etc.

[0119] Those skilled in the art can understand that Figure 7 the structure shown in the figure is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0120] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented:

[0121] Excite the scanning object multiple times and collect multiple sets of diffusion-weighted echo signals, and each set of diffusion-weighted echo signals corresponds to one excitation;

[0122] Obtain the phase information of each set of diffusion-weighted echo signals;

[0123] Correct the phase information of each set of diffusion-weighted echo signals to obtain the corrected phase information of each set of diffusion-weighted echo signals;

[0124] Perform image reconstruction according to each of the diffusion-weighted echo signals and the corrected phase information of each set of diffusion-weighted echo signals to obtain a magnetic resonance diffusion-weighted image.

[0125] For the computer device provided in the above embodiment, its implementation principle and technical effects are similar to those of the above method embodiment, and will not be described in detail here.

[0126] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0127] The scanning object is excited multiple times, and multiple sets of diffusion-weighted echo signals are acquired, with each set of diffusion-weighted echo signals corresponding to one excitation.

[0128] The phase information of each set of diffusion-weighted echo signals is obtained.

[0129] The phase information of each set of diffusion-weighted echo signals is corrected to obtain the corrected phase information of each set of diffusion-weighted echo signals.

[0130] Image reconstruction is performed based on each of the diffusion-weighted echo signals and the corrected phase information of each set of diffusion-weighted echo signals to obtain a magnetic resonance diffusion-weighted image.

[0131] The computer-readable storage medium provided in the above embodiment has the same implementation principle and technical effects as the above method embodiment, and will not be described in detail here.

[0132] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above method embodiments. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0133] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope described in this specification.

[0134] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation to the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the appended claims.

Claims

1. A magnetic resonance imaging method, characterized in that, The method includes: Performing multiple excitations on a scanned object and acquiring multiple sets of diffusion-weighted echo signals, with each set of diffusion-weighted echo signals corresponding to one excitation; Obtaining the phase information of each set of diffusion-weighted echo signals; Inputting each set of diffusion-weighted echo signals or the phase information of each set of diffusion-weighted echo signals into a preset neural network model to obtain the corrected phase information of each set of diffusion-weighted echo signals; Performing image reconstruction based on each of the diffusion-weighted echo signals and the corrected phase information of each set of diffusion-weighted echo signals to obtain a magnetic resonance diffusion-weighted image; The performing image reconstruction based on each of the diffusion-weighted echo signals and the corrected phase information of each set of diffusion-weighted echo signals to obtain a magnetic resonance diffusion-weighted image includes: Filling each of the diffusion-weighted echo signals into the same k-space to obtain k-space data; Obtaining the magnetic resonance diffusion-weighted image based on the k-space data and the corrected phase information of each set of diffusion-weighted echo signals.

2. The method according to claim 1, wherein Before the performing image reconstruction based on each of the diffusion-weighted echo signals and the corrected phase information of each set of diffusion-weighted echo signals to obtain a magnetic resonance diffusion-weighted image, the method further includes: Obtaining the physiological motion curve of the scanned object; Determining the weighting value of each set of diffusion-weighted echo signals according to the physiological motion curve, where the weighting value represents the filling proportion of each set of diffusion-weighted echo signals in the k-space.

3. The method according to claim 1, wherein The phase information of each set of diffusion-weighted echo signals is obtained by the following method: Performing a navigation sequence after each excitation of the scanned object and acquiring navigation signals; Obtaining the phase information of each set of diffusion-weighted echo signals according to the navigation signals.

4. The method according to claim 1, characterized in that The acquisition timing for acquiring each set of diffusion-weighted echo signals includes bipolar gradient timing or unipolar gradient timing.

5. The method according to claim 1, characterized in that Each set of diffusion-weighted echo signals corresponds to different phase encoding positions in the k-space.

6. A magnetic resonance imaging device, characterized in that, The device includes: An acquisition module, configured to perform multiple excitations on a scanned object and acquire multiple sets of diffusion-weighted echo signals, with each set of diffusion-weighted echo signals corresponding to one excitation; A first acquisition module, configured to obtain the phase information of each set of diffusion-weighted echo signals; A correction module, configured to input each set of diffusion-weighted echo signals or the phase information of each set of diffusion-weighted echo signals into a preset neural network model to obtain the corrected phase information of each set of diffusion-weighted echo signals; A reconstruction module, configured to perform image reconstruction based on each of the diffusion-weighted echo signals and the corrected phase information of each set of diffusion-weighted echo signals to obtain a magnetic resonance diffusion-weighted image; The reconstruction module includes: A first acquisition unit, configured to fill each of the diffusion-weighted echo signals into the same k-space to obtain k-space data; A reconstruction unit, configured to obtain the magnetic resonance diffusion-weighted image based on the k-space data and the corrected phase information of each set of diffusion-weighted echo signals.

7. The device according to claim 6, characterized in that, The device further includes: A second acquisition module, configured to obtain the physiological motion curve of the scanned object; A determination module, configured to determine the weighting value of each set of diffusion-weighted echo signals according to the physiological motion curve, where the weighting value represents the filling proportion of each set of diffusion-weighted echo signals in the k-space.

8. The device according to claim 6, characterized in that, The first acquisition module includes: An acquisition unit, configured to execute a navigation sequence after each excitation of the scanned object and acquire navigation signals; A third acquisition unit, configured to obtain the phase information of each group of diffusion-weighted echo signals according to the navigation signals.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the method according to any one of claims 1 to 5 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the method according to any one of claims 1 to 5 is implemented.

Images