Magnetic resonance imaging method and device

Abstract

The invention relates to a magnetic resonance imaging method and device. The method comprises the following steps: performing magnetic resonance scanning on a target object according to a preset sampling track to obtain multi-phase original scanning data of the target object; the original scanning data of different periods comprises scanning data of different slice layers of the target object; determining a coil sensitivity graph according to the original scanning data of each phase, and reconstructing the original scanning data of each phase according to the coil sensitivity graph to obtain a multi-phase scanning image of the target object; and performing magnetic resonance imaging based on the multi-phase scanning image. According to the method, the static high-definition imaging requirement and the dynamic high-definition imaging requirement can be met at the same time through one scanning process, and the multi-phase scanning image obtained through reconstruction can be suitable for various different imaging modes, so that magnetic resonance images in different imaging modes are obtained; the magnetic resonance imaging efficiency can be improved, and the magnetic resonance imaging effect can also be improved.

Description

Technical Field

[0001] This application relates to the field of magnetic resonance technology, and in particular to a magnetic resonance imaging method and apparatus. Background Technology

[0002] With the development of medical imaging technology, different imaging methods have emerged to meet various imaging needs. For example, magnetic resonance imaging (MRI) scans can be divided into static imaging and dynamic imaging based on their temporal resolution. Static imaging requires a longer scan time, and the image obtained in a single scan is an average of the patient's motion within the scanned area throughout the entire scan, failing to accurately reflect the true state of the scanned area. Dynamic imaging has a higher temporal resolution and can reflect the true motion of the scanned area, but its resolution is generally lower, resulting in poor detail, and it can only be used for observing motion.

[0003] Traditionally, magnetic resonance imaging (MRI) scans typically employ a single imaging modality to obtain the corresponding images. However, this modality cannot simultaneously satisfy the requirements for image detail and true-to-life representation, resulting in poor imaging quality. Summary of the Invention

[0004] Therefore, it is necessary to provide a magnetic resonance imaging method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can meet both the resolution requirements of static imaging and the temporal resolution requirements of dynamic imaging, thereby improving the imaging effect, in order to address the above-mentioned technical problems.

[0005] In a first aspect, this application provides a magnetic resonance imaging method, comprising:

[0006] The target object is subjected to magnetic resonance scanning according to the preset sampling trajectory to obtain the raw scan data of the target object in multiple phases; the raw scan data of different phases include the scan data of different slices of the target object;

[0007] The coil sensitivity map is determined based on the original scanning data of each phase, and the original scanning data of each phase is reconstructed based on the coil sensitivity map to obtain multi-phase scanning images of the target object.

[0008] Magnetic resonance imaging based on multi-phase scanning images.

[0009] In one embodiment, determining the coil sensitivity map based on the original scan data of each phase includes:

[0010] The original scan data of each phase are processed by time-weighted averaging to obtain intermediate scan data;

[0011] The coil sensitivity map is determined based on the intermediate scan data.

[0012] In one embodiment, the original scan data of each phase are subjected to a time-weighted average to obtain intermediate scan data, including:

[0013] Identify scan data of at least one phase belonging to the same slice from the raw scan data of each phase;

[0014] For each slice, the scan data of at least one phase of that slice are weighted and averaged to obtain the average scan data of the slice.

[0015] Intermediate scan data is generated based on the average scan data of each layer.

[0016] In one embodiment, the original scan data of each phase are reconstructed based on the coil sensitivity map to obtain a multi-phase scan image of the target object, including:

[0017] For each phase, the original scan data of that phase is reconstructed based on the coil sensitivity diagram to obtain the initial reconstructed image of that phase;

[0018] The initial reconstructed image of the phase is input into a preset reconstruction model for iterative reconstruction processing to obtain the scanned image of the phase.

[0019] In one embodiment, magnetic resonance imaging based on multi-phase scan images includes:

[0020] Acquire magnetic resonance imaging patterns;

[0021] Determine the magnetic resonance image corresponding to the magnetic resonance imaging mode based on multi-phase scanning images;

[0022] Display magnetic resonance images.

[0023] In one embodiment, if the magnetic resonance imaging mode includes a static imaging mode, determining the magnetic resonance image corresponding to the magnetic resonance imaging mode based on multi-phase scan images includes:

[0024] Arbitrarily select one phase scan image from multiple phase scan images as the magnetic resonance image corresponding to the static imaging mode; or...

[0025] Based on preset image quality requirements, a single scan image that meets the preset image quality requirements is selected from multiple phase scan images as the magnetic resonance image corresponding to the static imaging mode.

[0026] In one embodiment, if the magnetic resonance imaging mode includes a dynamic imaging mode, determining the magnetic resonance image corresponding to the magnetic resonance imaging mode based on multi-phase scan images includes:

[0027] Multi-phase scanning images are used as magnetic resonance images corresponding to dynamic imaging modes.

[0028] In one embodiment, if the magnetic resonance imaging mode includes a high-resolution imaging mode, determining the magnetic resonance image corresponding to the magnetic resonance imaging mode based on multi-phase scan images includes:

[0029] The multi-phase scan images are averaged to obtain the average scan image, which is then used as the magnetic resonance image corresponding to the high-definition imaging mode.

[0030] In one embodiment, the preset sampling trajectories are complementary and staggered in the phase direction, and the acceleration factor of the central region of K space is less than a first multiple threshold, while the acceleration factor of the non-central region of K space is greater than a second multiple threshold; wherein, the first multiple threshold is less than or equal to the second multiple threshold.

[0031] Secondly, this application also provides a magnetic resonance imaging device, comprising:

[0032] The scanning module is used to perform magnetic resonance scanning on the target object according to a preset sampling trajectory to obtain raw scanning data of the target object in multiple phases; the raw scanning data of different phases include scanning data of different slices of the target object;

[0033] The reconstruction module is used to determine the coil sensitivity map based on the original scanning data of each phase, and to reconstruct the original scanning data of each phase based on the coil sensitivity map to obtain multi-phase scanning images of the target object.

[0034] The imaging module is used for magnetic resonance imaging based on multi-phase scan images.

[0035] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the magnetic resonance imaging method in the first aspect described above.

[0036] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the magnetic resonance imaging method described in the first aspect above.

[0037] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the magnetic resonance imaging method described in the first aspect above.

[0038] The aforementioned magnetic resonance imaging method, apparatus, computer equipment, storage medium, and computer program product perform magnetic resonance scanning on a target object according to a preset sampling trajectory to obtain raw scan data of multiple phases of the target object. The raw scan data of different phases includes scan data of different slices of the target object. Then, a coil sensitivity map is determined based on the raw scan data of each phase, and the raw scan data of each phase is reconstructed based on the coil sensitivity map to obtain a multi-phase scan image of the target object. Magnetic resonance imaging is then performed based on the multi-phase scan image. Using the magnetic resonance imaging method proposed in this application, on the one hand, a preset sampling trajectory is used to collect raw scan data of multiple phases of the target object. This sampling trajectory enables rapid and complete data collection, ensuring both the data completeness of static imaging and the temporal resolution of dynamic imaging, providing a data foundation for subsequent image reconstruction. On the other hand, by determining the coil sensitivity map and reconstructing the image based on the raw scan data of multiple phases, a multi-phase scan image is obtained. This data processing method enables high-quality image reconstruction and obtains reconstructed images of multiple phases. Therefore, the magnetic resonance imaging method of this application can simultaneously meet the requirements of static high-definition imaging and dynamic high-definition imaging in a single scan process, and the reconstructed multi-phase scan images can be applied to a variety of different imaging modes, thereby obtaining magnetic resonance images under different imaging modes; it can not only improve the efficiency of magnetic resonance imaging, but also improve the magnetic resonance imaging effect and meet different clinical needs. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 This is a diagram illustrating the application environment of a magnetic resonance imaging method in one embodiment.

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

[0042] Figure 3 This is a flowchart illustrating a magnetic resonance imaging method in another embodiment;

[0043] Figure 4 This is a flowchart illustrating a magnetic resonance imaging method in another embodiment;

[0044] Figure 5 This is a flowchart illustrating a magnetic resonance imaging method in another embodiment;

[0045] Figure 6(a) is a schematic diagram of a magnetic resonance image in static imaging mode in one embodiment;

[0046] Figure 6(b) is a schematic diagram of a magnetic resonance image in dynamic imaging mode in one embodiment;

[0047] Figure 6(c) is a schematic diagram of a magnetic resonance image in the average imaging mode in one embodiment;

[0048] Figure 7 This is a schematic diagram of the complete process of a magnetic resonance imaging method in one embodiment;

[0049] Figure 8 This is a schematic diagram of the magnetic resonance imaging process in one embodiment;

[0050] Figure 9 This is a structural block diagram of a magnetic resonance imaging device in one embodiment;

[0051] Figure 10 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0053] With the development of medical imaging technology, different imaging methods have emerged to meet different imaging needs; for example, magnetic resonance imaging can be divided into static imaging and dynamic imaging according to the speed of imaging time resolution.

[0054] Traditional static MRI requires a long scan time, and the image obtained in a single scan is an average of the motion state during the acquisition time, making it difficult to accurately describe the actual situation of the scanned area. Traditional dynamic MRI, such as cardiac cine imaging and single-shot fast spin echo imaging, generally has lower resolution and poor detail due to limitations in acceleration capabilities, and can only be used for observing motion. In other words, static imaging is an average of the motion state throughout the entire scan process and cannot accurately reflect the true state of the scanned area; while dynamic imaging has higher temporal resolution and can reflect the true motion of the scanned area.

[0055] In addition, magnetic resonance imaging technology can be mainly divided into two types. One is the cinematic imaging technology based on the balanced steady-state free precession (BSSFP) sequence. Although it has a fast imaging speed and high temporal resolution, it has poor image contrast, low image resolution, and black band artifacts. The other is the single-excitation fast spin echo (FSE) sequence, which can achieve lateral relaxation time (T2) contrast, but the image resolution is not high, and the long echo train will cause the image to blur.

[0056] It is evident that while dynamic imaging offers high temporal resolution, it suffers from poor image resolution and low image quality. Furthermore, magnetic resonance imaging (MRI) scans are lengthy. Taking pelvic scans as an example, involuntary intestinal peristalsis easily generates artifacts, which patients cannot control. Some technicians administer anticholinergic drugs such as racemic scopolamine tablets during the scan to relax the pelvic floor muscles and inhibit intestinal peristalsis. However, these drugs have significant side effects, easily causing patients to be unable to urinate normally, resulting in a poor patient experience. Alternatively, some hospital technicians alleviate motion artifacts caused by intestinal peristalsis by prohibiting water intake, but artifacts still inevitably exist to some extent.

[0057] Furthermore, traditional magnetic resonance imaging (MRI) scans typically employ a single imaging method to obtain the corresponding images. This limitation restricts image viewing, as both static and dynamic imaging methods display images sequentially according to the scanned layers. To address these limitations of static and dynamic MRI scanning, this application proposes a novel whole-body live MRI imaging technology. This technology can be used for both high-definition static and rapid dynamic imaging, accurately reproducing the actual motion state of the scanned area in both modes, providing diagnostic physicians with high-quality and accurate objective evidence.

[0058] In addition, a new image browsing interaction method—live image browsing—is proposed for the live imaging technology proposed in this application. This image browsing interaction method is mainly divided into the following three modes: a. Static mode, in which only one phase image is displayed per layer, with the fewest number of images. This can be the default image browsing mode for live imaging, and the effect is consistent with traditional static imaging, which can meet most clinical scanning scenarios; b. Multi-phase dynamic browsing mode, in which images are displayed in the form of multiple phases according to the layer dimension, allowing users to observe the complete scanning process. This mode also has the largest number of images and is often used in scenarios where users need to observe the movement of the scanned area or the differences between adjacent phases to assist in decision-making; c. Averaging mode (also known as high-definition mode), in which the image displayed per layer is obtained by averaging multiple phases of that layer, resulting in the highest signal-to-noise ratio. This is generally used when the scanned area is almost static and the user wants to further improve the signal-to-noise ratio of the image.

[0059] The magnetic resonance imaging technology and image browsing interaction method proposed in this application allow users to quickly and flexibly switch between different image modes according to diagnostic needs, breaking through the limitations of the time dimension of existing magnetic resonance imaging.

[0060] The magnetic resonance imaging method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, the magnetic resonance imaging device 102 uses magnetic resonance imaging technology to perform a magnetic resonance scan on the object to be scanned, thereby obtaining a magnetic resonance image of the object. Exemplarily, the magnetic resonance imaging device 102 can employ the novel magnetic resonance imaging technology proposed in this application embodiment (which can be referred to as live magnetic resonance imaging), combining the resolution advantages of static imaging and the temporal resolution advantages of dynamic imaging. This allows it to simultaneously meet both static high-definition and dynamic high-definition clinical needs in a single scan, obtaining higher-quality magnetic resonance images and improving the magnetic resonance imaging effect.

[0061] In one exemplary embodiment, such as Figure 2 As shown, a magnetic resonance imaging method is provided, which is applied to... Figure 1 Taking a magnetic resonance imaging (MRI) device or its processor as an example, the explanation includes steps 202 to 206. Wherein:

[0062] Step 202: Perform magnetic resonance scanning on the target object according to the preset sampling trajectory to obtain the original scanning data of the target object in multiple phases.

[0063] The raw scan data from different phases includes scan data from different slices of the target object. That is, the raw scan data from different phases can include scan data from the same slice of the target object, or it can include scan data from different slices of the target object. For example, the sum of the raw scan data from different phases can cover scan data from all slices of the target object.

[0064] In one optional implementation, the preset sampling trajectories can be complementary and staggered in the phase direction, with the acceleration factor in the central region of K-space being less than a first multiple threshold, and the acceleration factor in the non-central region of K-space being greater than a second multiple threshold; wherein the first multiple threshold is less than or equal to the second multiple threshold. Using complementary and staggered sampling trajectories, original scan data of complementary and staggered multi-phase sequences can be obtained. For example, assuming the scanning phase includes a first phase and a second phase, the sampling trajectory could be that the first phase collects data from odd-numbered layers such as the first, third, and fifth layers, while the second phase collects data from even-numbered layers such as the second, fourth, and sixth layers. If there are more than two scanning phases, the corresponding layers in each phase are spatially interleaved or complementary. For example, the first phase collects data from the first, fourth, and seventh layers, the second phase collects data from the second, fifth, and eighth layers, and the third phase collects data from the third, sixth, and ninth layers. Of course, for multiple phases, the collected layer data can also include scanning data from the same layers; this application does not specifically limit this.

[0065] For example, when a preset sampling trajectory is obtained, a magnetic resonance scan of the target object can be performed according to the preset sampling trajectory to obtain raw scan data of multiple phases of the target object; the raw scan data of each phase includes scan data of multiple slices of the target object. Optionally, the raw scan data of each phase can be scan data obtained by high-magnification undersampling.

[0066] Step 204: Determine the coil sensitivity map based on the original scanning data of each phase, and reconstruct the original scanning data of each phase based on the coil sensitivity map to obtain a multi-phase scanning image of the target object.

[0067] For example, when the original scan data of multiple phases is obtained, a fully sampled K-space data can be obtained based on the original scan data of multiple phases. Then, the coil sensitivity map is determined based on the fully sampled K-space data. The coil sensitivity map can be used to characterize the sensitivity information of each coil.

[0068] Furthermore, once the coil sensitivity map is obtained, image reconstruction can be performed on the original scan data of each phase based on the coil sensitivity map to obtain the scan image of each phase, i.e., the multi-phase scan image of the target object.

[0069] For example, a preset image reconstruction model can be used to input the original scanning data of each phase and the coil sensitivity map into the preset image reconstruction model for processing, so as to obtain multi-phase scanning images of the target object.

[0070] Step 206: Perform magnetic resonance imaging based on multi-phase scan images.

[0071] For example, during imaging, different imaging modes such as static imaging, dynamic imaging, or averaging imaging can be performed.

[0072] In other words, magnetic resonance imaging (MRI) equipment can perform MRI based on the imaging mode and multi-phase scanning images to obtain MRI images; on this basis, MRI equipment can also output and display MRI images so that users can easily view the MRI images of the target object.

[0073] For example, before, after, or during a magnetic resonance scan, a user can select the imaging mode of the magnetic resonance imaging, so that the magnetic resonance imaging device can generate a magnetic resonance image corresponding to the imaging mode selected by the user based on the multi-phase scan images reconstructed from the scan.

[0074] For example, even if the user does not select an imaging mode for magnetic resonance imaging, the magnetic resonance imaging device can also generate a magnetic resonance image corresponding to the default imaging mode based on the multi-phase scan images reconstructed from the scan; wherein the default imaging mode may include at least one of static imaging, dynamic imaging, and averaging imaging.

[0075] For example, when a magnetic resonance imaging (MRI) device generates an MRI image corresponding to an imaging mode, it can also output and display the MRI image. In an optional implementation, the MRI device can send the generated MRI image corresponding to the imaging mode to a display device for output and display. The display device may include a display screen communicatively connected to the MRI device, a wearable device communicatively connected to the MRI device, etc. The wearable device may include a smartwatch, a smart bracelet, and a smart head-mounted device, etc. These wearable devices can output and display MRI images based on extended reality technology, or they can output and display MRI images based on projection technology, etc. The embodiments of this application do not specifically limit this.

[0076] In the aforementioned magnetic resonance imaging method, a magnetic resonance scan of the target object is performed according to a preset sampling trajectory to obtain raw scan data of multiple phases of the target object. The raw scan data of different phases includes scan data of different slices of the target object. Then, a coil sensitivity map is determined based on the raw scan data of each phase, and the raw scan data of each phase is reconstructed based on the coil sensitivity map to obtain a multi-phase scan image of the target object. Magnetic resonance imaging is then performed based on the multi-phase scan image. Using the magnetic resonance imaging method proposed in this application, on the one hand, a preset sampling trajectory is used to collect raw scan data of multiple phases of the target object. This sampling trajectory enables rapid and complete data collection, ensuring both the data completeness of static imaging and the temporal resolution of dynamic imaging, providing a data foundation for subsequent image reconstruction. On the other hand, by determining the coil sensitivity map and reconstructing the image based on the raw scan data of multiple phases, a multi-phase scan image is obtained. This data processing method enables high-quality image reconstruction and yields reconstructed images of multiple phases. Therefore, the magnetic resonance imaging method of this application can simultaneously meet the requirements of static high-definition imaging and dynamic high-definition imaging in a single scan process, and the reconstructed multi-phase scan images can be applied to a variety of different imaging modes, thereby obtaining magnetic resonance images under different imaging modes; it can not only improve the efficiency of magnetic resonance imaging, but also improve the magnetic resonance imaging effect and meet different clinical needs.

[0077] In one exemplary embodiment, such as Figure 3 As shown, step 204 above, which involves determining the coil sensitivity map based on the original scan data of each phase, may include steps 302 to 304. Wherein:

[0078] Step 302: Perform time-weighted averaging on the original scan data of each phase to obtain intermediate scan data.

[0079] For example, during magnetic resonance imaging (MRI) scanning, the acquired raw data, i.e., the raw scan data of multiple phases, can be undersampled data. By preprocessing the raw scan data of multiple phases, fully sampled intermediate scan data can be obtained. Based on this, for the raw scan data of each phase, preprocessing can be performed first to obtain preprocessed intermediate scan data. The preprocessing can include at least one data processing method, and the intermediate scan data can be fully sampled K-space data.

[0080] For example, preprocessing may include performing time-weighted averaging on the raw scan data of multiple phases; based on this, the magnetic resonance imaging device can obtain fully sampled intermediate scan data by performing time-weighted averaging on the raw scan data of each phase.

[0081] In one alternative implementation, during time-weighted processing, the magnetic resonance imaging (MRI) device can determine at least one phase belonging to the same slice from the raw scan data of each phase. Then, for each slice, a weighted average of the scan data of at least one phase in that slice is performed to obtain the average scan data for that slice. Subsequently, intermediate scan data is generated based on the average scan data of each slice. In other words, the average scan data corresponding to each slice is determined from the raw scan data of multiple phases, and then the average scan data of each slice are merged to obtain fully sampled intermediate scan data.

[0082] Step 304: Determine the coil sensitivity map based on the intermediate scan data.

[0083] In other words, given the full-sample intermediate scan data, the sensitivity information of each coil can be determined based on the full-sample intermediate scan data, thus obtaining the coil sensitivity map.

[0084] In this embodiment, when the magnetic resonance imaging device acquires raw scan data of multiple phases through undersampling, it can first perform data preprocessing on the raw scan data of these multiple phases to obtain intermediate scan data in full-sampling K-space; then, the coil sensitivity map is determined based on the fully sampled intermediate scan data. Using the method in this embodiment, data acquisition through undersampling and determination of the coil sensitivity map through preprocessing not only improves the efficiency of data acquisition but also enhances the accuracy of coil sensitivity map determination.

[0085] In one exemplary embodiment, such as Figure 4 As shown, step 202 above, which involves reconstructing the original scan data of each phase based on the coil sensitivity diagram to obtain a multi-phase scan image of the target object, may include steps 402 to 404. Wherein:

[0086] Step 402: For each phase, reconstruct the original scan data of that phase based on the coil sensitivity diagram to obtain the initial reconstructed image of that phase.

[0087] For example, a magnetic resonance imaging (MRI) device can employ a preset image reconstruction algorithm to reconstruct images of the original scan data for each phase based on the coil sensitivity map, thereby obtaining an initial reconstructed image for each phase. The preset image reconstruction algorithm can be any image reconstruction algorithm in the related art, and this application embodiment does not specifically limit it.

[0088] Step 404: Input the initial reconstructed image of the phase into the preset reconstruction model for iterative reconstruction processing to obtain the scanned image of the phase.

[0089] For example, the preset reconstruction model can be any model, such as a deep learning model or a machine learning model; for instance, the preset reconstruction model can be a deep learning iterative reconstruction model based on a physical model, which can consist of two parts: a data consistency term and a deep learning network; wherein, the purpose of the data consistency term is to ensure that the result of each iteration is consistent with the actual collected data, for example, argmin||Ax-b|| can be solved by conjugate gradient descent. 2 Where A is an operator containing the sampling trajectory and Fourier transform of the real-world image, b is the K-space data of the actual acquired real-world image, x is the K-space data to be solved, and argmin represents the minimum value operation. 2 This represents the L2 norm operation. The deep learning network part can be a three-dimensional convolutional network based on U-Net. Based on this reconstruction model, for each phase, the initial reconstructed image and coil sensitivity map of that phase can be used as inputs to the reconstruction model for iterative reconstruction until a real image that meets the preset iteration stopping condition is obtained, which is then used as the scan image of that phase.

[0090] For example, the preset iteration stopping condition may include, but is not limited to, a preset number of iterations, a preset loss threshold, and a preset image quality requirement.

[0091] In this embodiment, when reconstructing multi-phase scanning images, for each phase, the original scanning data of that phase can be reconstructed first according to the coil sensitivity diagram to obtain the initial reconstructed image of that phase; then the initial reconstructed image of that phase is input into a preset reconstruction model for iterative reconstruction processing to obtain the scanning image of that phase; by using this method to reconstruct the scanning image of each phase, a multi-phase scanning image can be obtained, which can improve the image reconstruction efficiency and the quality of the reconstructed image.

[0092] In one exemplary embodiment, such as Figure 5 As shown, step 206 above may include steps 502 to 506. Wherein:

[0093] Step 502: Obtain the magnetic resonance imaging mode.

[0094] The magnetic resonance imaging mode can include at least one of the following: static imaging mode, dynamic imaging mode, and average imaging mode.

[0095] For example, before imaging, the user can select the desired magnetic resonance imaging mode so that the magnetic resonance imaging device can obtain the magnetic resonance imaging mode selected or input by the user; it should be noted that before imaging, it can be before the magnetic resonance imaging device performs the above step 206.

[0096] For example, if the user does not select the desired magnetic resonance imaging mode before imaging, the magnetic resonance imaging device can also obtain the default magnetic resonance imaging mode.

[0097] For example, after the magnetic resonance imaging device performs imaging according to the magnetic resonance imaging mode selected by the user or the default magnetic resonance imaging mode, if the user wants to change the magnetic resonance imaging mode or view scan images of other magnetic resonance imaging modes, the user can reselect or modify the magnetic resonance imaging mode so that the magnetic resonance imaging device performs imaging according to the reselected or modified magnetic resonance imaging mode.

[0098] Step 504: Determine the magnetic resonance image corresponding to the magnetic resonance imaging mode based on the multi-phase scanning images.

[0099] For example, when the magnetic resonance imaging mode includes a static imaging mode, the magnetic resonance imaging device can arbitrarily select one phase scan image from multiple phase scan images as the magnetic resonance image corresponding to the static imaging mode; or, according to preset image quality requirements, it can select one phase scan image from multiple phase scan images that meets the preset image quality requirements as the magnetic resonance image corresponding to the static imaging mode. The magnetic resonance image corresponding to the static imaging mode includes scan images of multiple slices.

[0100] For example, the preset image quality requirements may include at least one requirement related to image quality, such as signal-to-noise ratio requirements, brightness requirements, and contrast requirements. For instance, recommendations can be made based on the signal-to-noise ratio, such as recommending the image with the best signal-to-noise ratio. Alternatively, deep learning can be used for comprehensive judgment to recommend the image with the best overall quality. Or, based on the motion of the scanned area, the optimal image can be recommended through registration technology.

[0101] Referring to Figure 6(a), the left side shows a traditional static scan. Due to peristalsis in the rectum and uterus, the details of the uterine and rectal walls are blurred. In clinical practice, when encountering such cases, the patient needs to be rescanned. If the scan still fails, an anti-peristaltic drug, such as anisodamine, needs to be injected. The right side shows an image obtained through live magnetic resonance imaging in static mode. Because live imaging has a high temporal resolution, it can freeze the peristalsis of the uterus and rectum, achieving clear imaging of the endometrium and rectal wall.

[0102] For example, when the magnetic resonance imaging mode includes a dynamic imaging mode, the magnetic resonance imaging device can use multi-phase scan images as the magnetic resonance images corresponding to the dynamic imaging mode. Each phase scan image includes scan images of multiple slices.

[0103] Referring to Figure 6(b), which shows a dynamic imaging schematic of the temporomandibular joint, from left to right are reconstructed real-world images of different phases obtained by scanning in chronological order, with the circled area representing the temporomandibular joint.

[0104] Traditional static scanning only yields a single image of the temporomandibular joint fixed at a specific angle (a single phase image), unlike dynamic imaging which allows observation of joint movement. The diagnosis of temporomandibular joint disorder, joint dislocation, and other conditions heavily relies on dynamic imaging parameters. Live imaging's dynamic mode easily provides cinematic images of the scanned area.

[0105] For example, when the magnetic resonance imaging mode includes an averaging imaging mode, the magnetic resonance imaging device can perform averaging processing on multi-phase scan images to obtain an average scan image, and use the average scan image as the magnetic resonance image corresponding to the averaging imaging mode. Specifically, the averaging processing involves averaging multiple scan images belonging to the same slice within the multi-phase scan images to obtain the average scan image of that slice; then, the magnetic resonance image corresponding to the averaging imaging mode is obtained based on the average scan image of each slice; wherein the magnetic resonance image corresponding to the averaging imaging mode includes average scan images of multiple slices.

[0106] For example, when performing averaging, the mean can be calculated for all phases of each layer, or the averaging can be achieved by calculating the root mean square pixel by pixel.

[0107] Referring to Figure 6(c), the left side is a cervical spine transverse image obtained by live imaging. The area indicated by the arrow is the spinal cord. The user wants to observe the spinal cord morphology, which is to show a bright signal throughout. However, due to the flow void effect of the FSE sequence, it cannot be guaranteed that the cerebrospinal fluid in each image is a bright signal. A bright spinal cord signal can be obtained by averaging the live imaging mode.

[0108] Step 506: Display the magnetic resonance image.

[0109] For example, a magnetic resonance imaging device can output and display the magnetic resonance image corresponding to a magnetic resonance imaging mode; when there are multiple magnetic resonance imaging modes, the magnetic resonance imaging device can display the magnetic resonance images corresponding to multiple magnetic resonance imaging modes simultaneously, or it can display the magnetic resonance images corresponding to multiple magnetic resonance imaging modes sequentially.

[0110] Optionally, when displaying magnetic resonance imaging (MRI) images corresponding to multiple MRI modes sequentially, the MRI device can display the MRI images corresponding to each MRI mode according to a preset time interval and a preset display order; alternatively, it can display the MRI images corresponding to each MRI mode sequentially upon user triggering. For example, when the user triggers the next image, the MRI device displays the MRI image corresponding to the next MRI mode of the current MRI mode; when the user triggers the previous image, the MRI device displays the MRI image corresponding to the previous MRI mode of the current MRI mode.

[0111] In this embodiment, the magnetic resonance imaging (MRI) device can acquire the MRI mode and determine the MRI image corresponding to the MRI mode based on multi-phase scan images, and then display the MRI image. In other words, the MRI method proposed in this application embodiment is applicable to imaging needs under various different imaging modes and can perform targeted imaging according to different user needs, improving the universality and flexibility of MRI.

[0112] In one exemplary embodiment, a complete embodiment of magnetic resonance imaging is provided. Reference Figure 7 As shown, it illustrates a flowchart of a magnetic resonance imaging method, which includes:

[0113] Step 1, Data Collection

[0114] Unlike traditional static magnetic resonance sampling trajectories, the live imaging in this embodiment collects data through a specially designed sampling trajectory. This sampling trajectory is complementary and interlaced in the phase direction, and the acceleration factor is low in the central low-frequency region of K-space and high in the high-frequency part on both sides. After scanning using this specially designed sampling trajectory, multiple phase raw scan data can be obtained, and there are different layers of scan data between the raw scan data of each phase.

[0115] Additionally, it should be noted that by setting a lower acceleration factor in the low-frequency region at the center of the K-space and a higher acceleration factor in the high-frequency regions on both sides, it is possible to ensure that more data in the low-frequency region is collected, while less data in the high-frequency region is collected. This not only ensures the integrity of the collected data and guarantees the resolution of the reconstructed image, but also improves the data acquisition efficiency.

[0116] Step 2, Data Preprocessing

[0117] After data acquisition via the aforementioned preset sampling trajectory, the raw scan data for each phase is high-magnification under-sampled data. Therefore, a series of image preprocessing steps are required to obtain initial reconstructed data before subsequent iterative reconstruction can proceed. Optionally, a time-weighted average can be applied to the acquired raw scan data across multiple phases (i.e., for each layer of data, a weighted average of data from the same layer across multiple phases) to obtain fully sampled K-space data. A coil sensitivity map is then obtained based on this fully sampled K-space data. This coil sensitivity map can be used to initialize the reconstruction of the raw scan data for each phase, resulting in an initial reconstructed image for each phase. This initial reconstructed image and the coil sensitivity map can be used as inputs for the image reconstruction part, ultimately yielding the final reconstructed image for each phase.

[0118] Step 3, Image Reconstruction

[0119] The image reconstruction can employ a deep learning iterative reconstruction module based on a physical model. This module consists of two parts: a data consistency term and a deep learning network. For each phase, the initial reconstructed image and coil sensitivity map of that phase are input into the deep learning iterative reconstruction module for iterative reconstruction processing. After a series of iterative reconstructions, a high-resolution, artifact-free scanned image corresponding to that phase can be obtained.

[0120] Step 4, Live Images

[0121] After iterative processing by the image reconstruction module, multi-phase scan images (also known as live images) are obtained. These multi-phase scan images can have three imaging display modes: "static mode," "dynamic mode," and "averaging mode." Users can switch between different image browsing modes for the live images. When users need to observe static imaging images, a specific phase from the multi-phase scan images can be recommended, i.e., static mode; when users need to observe the dynamic imaging process, the multi-phase scan images can be played in a dynamic loop, i.e., dynamic mode, also known as movie mode. In addition, users can also obtain an image with a higher signal-to-noise ratio through averaging processing, i.e., averaging mode, also known as high-definition mode.

[0122] With the live images from the three modes mentioned above, users can either view the image statically through a single phase or assess the motion state of the scanned area by observing the continuous changes across all phases, providing activity indicators for clinical diagnosis.

[0123] refer to Figure 8As shown, this illustrates an imaging display method. For example, during magnetic resonance imaging (MRI), static and dynamic imaging can be performed by default. That is, the MRI device can determine the MRI image corresponding to the static imaging mode and the MRI image corresponding to the dynamic imaging mode based on multi-phase scan images; and output and display the MRI images corresponding to the static imaging mode and the dynamic imaging mode.

[0124] Based on this, if a user wants to view magnetic resonance images in other modes, they can switch imaging modes to obtain the magnetic resonance images corresponding to the new imaging mode. For example, the magnetic resonance imaging device can simultaneously output and display the magnetic resonance images corresponding to the two default imaging modes and the magnetic resonance image corresponding to the new imaging mode. Alternatively, the magnetic resonance image corresponding to the default static imaging mode can be replaced with the magnetic resonance image corresponding to the new imaging mode, at which point the interface displays the magnetic resonance image corresponding to the new imaging mode and the magnetic resonance image corresponding to the dynamic imaging mode. Or, the magnetic resonance image corresponding to the default dynamic imaging mode can be replaced with the magnetic resonance image corresponding to the new imaging mode, at which point the interface displays the magnetic resonance image corresponding to the new imaging mode and the magnetic resonance image corresponding to the static imaging mode.

[0125] It should be noted that, for the default static imaging mode, static magnetic resonance images can also be obtained using traditional static imaging methods, or static magnetic resonance images can be obtained using artificial intelligence methods based on deep learning, etc.

[0126] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0127] Based on the same inventive concept, this application also provides a magnetic resonance imaging apparatus for implementing the magnetic resonance imaging method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more magnetic resonance imaging apparatus embodiments provided below can be found in the limitations of the magnetic resonance imaging method described above, and will not be repeated here.

[0128] In one exemplary embodiment, such as Figure 9 As shown, a magnetic resonance imaging device is provided, including: a scanning module 902, a reconstruction module 904, and an imaging module 906, wherein:

[0129] The scanning module 902 is used to perform magnetic resonance scanning on the target object according to the preset sampling trajectory to obtain the original scanning data of the target object in multiple phases; the original scanning data of different phases include the scanning data of different slices of the target object.

[0130] The reconstruction module 904 is used to determine the coil sensitivity map based on the original scanning data of each phase, and to reconstruct the original scanning data of each phase based on the coil sensitivity map to obtain a multi-phase scanning image of the target object.

[0131] Imaging module 906 is used for magnetic resonance imaging based on multi-phase scan images.

[0132] In one embodiment, the reconstruction module 904 includes:

[0133] The processing unit is used to perform time-weighted averaging on the raw scan data of each phase to obtain intermediate scan data.

[0134] The determination unit is used to determine the coil sensitivity map based on the intermediate scan data.

[0135] In one embodiment, the processing unit is specifically configured to determine, from the original scan data of each phase, at least one phase belonging to the same slice; for each slice, perform a weighted average processing on the scan data of at least one phase of that slice to obtain the average scan data of the slice; and generate intermediate scan data based on the average scan data of each slice.

[0136] In one embodiment, the reconstruction module 904 further includes:

[0137] The first reconstruction unit is used to reconstruct the original scan data of each phase based on the coil sensitivity diagram to obtain the initial reconstructed image of that phase.

[0138] The second reconstruction unit is used to input the initial reconstruction image of the phase into a preset reconstruction model for iterative reconstruction processing to obtain the scanned image of the phase.

[0139] In one embodiment, the imaging module 906 includes:

[0140] Acquisition unit, used to acquire magnetic resonance imaging patterns;

[0141] The determination unit is used to determine the magnetic resonance image corresponding to the magnetic resonance imaging mode based on multi-phase scanning images;

[0142] The display unit is used to display magnetic resonance images.

[0143] In one embodiment, if the magnetic resonance imaging mode includes a static imaging mode, the determining unit is used to arbitrarily select one phase scan image from the multi-phase scan images as the magnetic resonance image corresponding to the static imaging mode; or, according to preset image quality requirements, select one phase scan image from the multi-phase scan images that meets the preset image quality requirements as the magnetic resonance image corresponding to the static imaging mode.

[0144] In one embodiment, if the magnetic resonance imaging mode includes a dynamic imaging mode, the determining unit is used to use the multi-phase scan image as the magnetic resonance image corresponding to the dynamic imaging mode.

[0145] In one embodiment, if the magnetic resonance imaging mode includes a high-definition imaging mode, the determining unit is used to perform averaging processing on the multi-phase scan images to obtain an average scan image, and use the average scan image as the magnetic resonance image corresponding to the high-definition imaging mode.

[0146] In one embodiment, the preset sampling trajectories are complementary and staggered in the phase direction, and the acceleration factor of the central region of K space is less than a first multiple threshold, while the acceleration factor of the non-central region of K space is greater than a second multiple threshold; wherein, the first multiple threshold is less than or equal to the second multiple threshold.

[0147] Each module in the aforementioned magnetic resonance imaging device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0148] In one exemplary embodiment, a computer device is provided, which may be a magnetic resonance imaging device, and its internal structure diagram may be as follows: Figure 10As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a magnetic resonance imaging method. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0149] Those skilled in the art will understand that Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0150] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the magnetic resonance imaging method in any of the above embodiments.

[0151] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the magnetic resonance imaging method in any of the above embodiments.

[0152] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the magnetic resonance imaging method in any of the above embodiments.

[0153] It should be noted that the data involved in this application (including but not limited to data used for analysis, data stored, data displayed, etc.) are all information and data that have been fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0154] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0155] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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, they should be considered to be within the scope of this specification.

[0156] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A magnetic resonance imaging method, characterized in that, The method includes: The target object is subjected to magnetic resonance scanning according to a preset sampling trajectory to obtain raw scan data of multiple phases of the target object; the raw scan data of different phases include scan data of different slices of the target object; The coil sensitivity map is determined based on the original scanning data of each phase, and the original scanning data of each phase is reconstructed based on the coil sensitivity map to obtain a multi-phase scanning image of the target object. Magnetic resonance imaging is performed based on the multi-phase scan images.

2. The method according to claim 1, characterized in that, The determination of the coil sensitivity map based on the original scan data of each phase includes: The original scan data of each phase are processed by time-weighted averaging to obtain intermediate scan data; The coil sensitivity map is determined based on the intermediate scan data.

3. The method according to claim 2, characterized in that, The intermediate scan data is obtained by performing a time-weighted average of the original scan data for each of the aforementioned phases, including: From the original scan data of each of the aforementioned phases, determine the scan data of at least one phase belonging to the same slice; For each slice, the scan data of at least one phase of the slice are weighted and averaged to obtain the average scan data of the slice. The intermediate scan data is generated based on the average scan data of each of the aforementioned layers.

4. The method according to claim 1, characterized in that, The step of reconstructing the original scan data of each phase based on the coil sensitivity map to obtain a multi-phase scan image of the target object includes: For each of the aforementioned phases, the original scan data of the phase is reconstructed based on the coil sensitivity diagram to obtain an initial reconstructed image of the phase; The initial reconstructed image of the phase is input into a preset reconstruction model for iterative reconstruction processing to obtain the scanned image of the phase.

5. The method according to claim 1, characterized in that, The magnetic resonance imaging based on the multi-phase scan images includes: Acquire magnetic resonance imaging patterns; Based on the multi-phase scan images, determine the magnetic resonance image corresponding to the magnetic resonance imaging mode; The magnetic resonance image is displayed.

6. The method according to claim 5, characterized in that, If the magnetic resonance imaging mode includes a static imaging mode, then determining the magnetic resonance image corresponding to the magnetic resonance imaging mode based on the multi-phase scan images includes: Arbitrarily select one phase scan image from the multi-phase scan images as the magnetic resonance image corresponding to the static imaging mode; or... According to the preset image quality requirements, a single-phase scan image that meets the preset image quality requirements is selected from the multi-phase scan images as the magnetic resonance image corresponding to the static imaging mode.

7. The method according to claim 5, characterized in that, If the magnetic resonance imaging mode includes a dynamic imaging mode, then determining the magnetic resonance image corresponding to the magnetic resonance imaging mode based on the multi-phase scan images includes: The multi-phase scan images are used as the magnetic resonance images corresponding to the dynamic imaging mode.

8. The method according to claim 5, characterized in that, If the magnetic resonance imaging mode includes a high-resolution imaging mode, then determining the magnetic resonance image corresponding to the magnetic resonance imaging mode based on the multi-phase scan images includes: The multi-phase scan images are averaged to obtain an average scan image, which is then used as the magnetic resonance image corresponding to the high-definition imaging mode.

9. The method according to any one of claims 1-8, characterized in that, The preset sampling trajectories are complementary and staggered in the phase direction, and the acceleration factor of the central region of K space is less than the first multiple threshold, while the acceleration factor of the non-central region of K space is greater than the second multiple threshold; wherein, the first multiple threshold is less than or equal to the second multiple threshold.

10. A magnetic resonance imaging device, characterized in that, The device includes: The scanning module is used to perform magnetic resonance scanning on the target object according to a preset sampling trajectory to obtain raw scanning data of the target object in multiple phases; the raw scanning data of different phases include scanning data of different slices of the target object; The reconstruction module is used to determine the coil sensitivity map based on the original scanning data of each phase, and to reconstruct the original scanning data of each phase based on the coil sensitivity map to obtain a multi-phase scanning image of the target object. An imaging module is used for magnetic resonance imaging based on the multi-phase scan images.

Images