Magnetic resonance imaging scanning method and device, computer equipment and storage medium

Abstract

The invention relates to a magnetic resonance imaging scanning method and device, computer equipment, a storage medium and a computer program product. The method comprises the steps of obtaining a positioning image of a detection object; identifying part boundary information corresponding to the target part in the positioning image; the target part comprises a left area and a right area which are separated from each other; setting a shimming frame according to the part boundary information; the shimming frame extends from the edge of the left area to the edge of the right area; and executing calibration operation in the shimming frame coverage area. By adopting the method, the shimming operation intelligence in the magnetic resonance imaging scanning process can be improved.

Description

Technical Field

[0001] The present application relates to the field of medical imaging technology, and in particular to a magnetic resonance imaging scanning method, apparatus, computer equipment, storage medium and computer program product. Background Art

[0002] During magnetic resonance imaging, in order to improve the image quality of the scanning area, it is necessary to perform field shimming operation on the scanning area.

[0003] At present, in the related technology, for the shim operation, since the size of the shim frame is fixed to the size of the image shim frame, the position of the shim frame can only be roughly determined according to the position of the FOV (Field of view). When the position of the shim frame is inaccurate, the scanning technician needs to manually adjust the position and range of the shim frame, which may result in the need to adjust the operational details of the shim operation back and forth, affecting the scanning efficiency and scanning accuracy.

[0004] Therefore, the related technology has the problem of low intelligence of shimming operation during the magnetic resonance imaging scanning process. Summary of the invention

[0005] Based on this, it is necessary to provide a magnetic resonance imaging scanning method, apparatus, computer equipment, computer-readable storage medium and computer program product that can intelligently perform shim operation during magnetic resonance imaging scanning in order to solve the above technical problems.

[0006] In a first aspect, the present application provides a magnetic resonance imaging scanning method. The method comprises:

[0007] Acquire a positioning image of the detection object;

[0008] Identifying part boundary information corresponding to a target part in the positioning image; the target part includes a left area and a right area separated from each other;

[0009] According to the part boundary information, a shim frame is set; the shim frame extends from an edge of the left area to an edge of the right area;

[0010] A calibration operation is performed in the area covered by the shim frame.

[0011] In one embodiment, setting a shim frame according to the part boundary information includes:

[0012] According to the part boundary information, an initial shim frame is adjusted to surround the target part in the scout image to obtain a target shim frame; the target shim frame extends from the edge of the left area to the edge of the right area.

[0013] In one embodiment, adjusting the initial shim frame to surround the target part in the scout image according to the part boundary information to obtain the target shim frame includes:

[0014] According to the part boundary information, adjusting the size and position of the initial shim frame;

[0015] When the adjusted initial shim frame surrounds the target part in the scout image, the target shim frame is obtained.

[0016] In one embodiment, when the adjusted initial shim frame surrounds the target part in the scout image, obtaining the target shim frame includes:

[0017] When the distance between the upper and lower boundaries of the adjusted initial shim frame and the upper and lower boundaries corresponding to the part boundary information, and when the distance between the left and right boundaries of the adjusted initial shim frame and the left and right boundaries corresponding to the part boundary information is less than a preset distance threshold, it is determined that the adjusted initial shim frame surrounds the target part in the positioning image.

[0018] In one embodiment, the method further comprises:

[0019] According to the part boundary information, a pre-pulse module frame is set; the upper boundary of the pre-pulse module frame is flush with the edge corresponding to the upper boundary point in the part boundary information;

[0020] A calibration operation is performed in the pre-pulse module frame coverage area.

[0021] In one embodiment, the method further comprises:

[0022] Screening out, from the tomographic images corresponding to the target part, a tomographic image matching the boundary information of the part as a target tomographic image;

[0023] The three-dimensional target part blood vessel morphology is obtained according to the target part artery boundary information segmented from each of the target tomographic images.

[0024] In a second aspect, the present application also provides a magnetic resonance imaging scanning device. The device comprises:

[0025] An acquisition module, used for acquiring a positioning image of the detection object;

[0026] An identification module, used for identifying part boundary information corresponding to a target part in the positioning image; the target part includes a left area and a right area separated from each other;

[0027] A setting module, configured to set a shim frame according to the part boundary information; the shim frame extends from an edge of the left region to an edge of the right region;

[0028] An execution module is used to perform a calibration operation in the area covered by the shim frame.

[0029] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0030] Acquire a positioning image of the detection object;

[0031] Identifying part boundary information corresponding to a target part in the positioning image; the target part includes a left area and a right area separated from each other;

[0032] According to the part boundary information, a shim frame is set; the shim frame extends from an edge of the left area to an edge of the right area;

[0033] A calibration operation is performed in the area covered by the shim frame.

[0034] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0035] Acquire a positioning image of the detection object;

[0036] Identifying part boundary information corresponding to a target part in the positioning image; the target part includes a left area and a right area separated from each other;

[0037] According to the part boundary information, a shim frame is set; the shim frame extends from an edge of the left area to an edge of the right area;

[0038] A calibration operation is performed in the area covered by the shim frame.

[0039] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0040] Acquire a positioning image of the detection object;

[0041] Identifying part boundary information corresponding to a target part in the positioning image; the target part includes a left area and a right area separated from each other;

[0042] According to the part boundary information, a shim frame is set; the shim frame extends from an edge of the left area to an edge of the right area;

[0043] A calibration operation is performed in the area covered by the shim frame.

[0044] The magnetic resonance imaging scanning method, apparatus, computer equipment, storage medium and computer program product are configured to obtain a positioning image of the detection object; identify part boundary information corresponding to the target part in the positioning image; the target part includes a left area and a right area separated from each other; set a shim frame according to the part boundary information; the shim frame extends from the edge of the left area to the edge of the right area; and perform a calibration operation in the area covered by the shim frame.

[0045] In this way, by identifying the part boundary information corresponding to the target part in the positioning image of the detection object, the shape, position and size of the target part can be identified, so that the shimming frame is set according to the part boundary information, and the position placement and size of the shimming frame are automatically adjusted by using the shape, position and size of the target part, so that the set shimming frame extends from the edge of the left area of ​​the target part to the edge of the right area of ​​the target part, and can not only surround the target part body but also surround the artery, spine and other part structures between the left area and the right area of ​​the target part body, and not only can the shimming range be accurately determined, but also the information related to the target part can be more comprehensively obtained. And by performing the calibration operation in the set shimming frame coverage area, accurate shimming is achieved, the image quality of the scanning area where the target part is located is improved, and there is no need for the user to manually and repeatedly adjust the position and size of the shimming frame, the efficiency of the shimming operation is improved, and thus the intelligence of the shimming operation in the magnetic resonance imaging scanning process is effectively improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 is a schematic flow chart of a magnetic resonance imaging scanning method in one embodiment;

[0047] Figure 2 A flowchart of a magnetic resonance imaging scanning method for kidney area in one embodiment;

[0048] Figure 3 is a schematic flow chart of a magnetic resonance imaging scanning method for kidneys in one embodiment;

[0049] Figure 4 It is a schematic diagram of a process of performing image post-processing on a tomographic image corresponding to a kidney part in one embodiment;

[0050] Figure 5 A schematic diagram of collecting a scanning sequence in one embodiment;

[0051] Figure 6 is a schematic flow chart of a magnetic resonance imaging scanning method in another embodiment;

[0052] Figure 7 is a structural block diagram of a magnetic resonance imaging scanning device in one embodiment;

[0053] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with 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] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0056] In one embodiment, Figure 1 As shown, a magnetic resonance imaging scanning method is provided. This embodiment uses the method applied to a magnetic resonance system as an example for illustration. The magnetic resonance system may be a system with a magnetic resonance scanning function such as an MR (Magnetic Resonance) system, a PET (Positron Emission Tomography) / MR system, etc. In this embodiment, the method includes the following steps:

[0057] Step S110, obtaining a positioning image of the detection object.

[0058] The positioning image may be a three-dimensional (3D) positioning image.

[0059] The positioning image may be an image of a larger range (eg, from head to toe, from neck to abdomen, from chest to abdomen) obtained by performing a positioning scan on the detection object by the magnetic resonance system.

[0060] The positioning image corresponding to the detection object can be pre-stored in the memory of the magnetic resonance system, and the magnetic resonance system can directly obtain it from the memory when needed. It is understandable that the magnetic resonance system can also obtain the positioning image obtained by positioning scanning the detection object in real time.

[0061] In a specific implementation, the magnetic resonance system may acquire a positioning image obtained by performing a positioning scan on the detection object, and the positioning image may include a target part of the detection object.

[0062] Step S120: identifying part boundary information corresponding to the target part in the positioning image.

[0063] The target part may be an organ part with a symmetrical structure, and thus the target part includes a left region and a right region separated from each other. For example, the target part may be a kidney part, a lung part, and the like.

[0064] The part boundary information corresponding to the target part may include part boundary information corresponding to the left area and part boundary information corresponding to the right area.

[0065] The part boundary information is information used to characterize the boundary contour of the target part, and may include the position information of the boundary points constituting the boundary contour of the target part, that is, the position information of the boundary points constituting the boundary contour of the left region and the position information of the boundary points constituting the boundary contour of the right region.

[0066] The part boundary information may include upper and lower boundary information and left and right boundary information. As an optional embodiment of the present application, the part boundary information may also include front and back boundary information.

[0067] In a specific implementation, the magnetic resonance system can identify the part boundary information corresponding to the target part in the positioning image. Specifically, taking the positioning image as a 3D positioning image as an example, the magnetic resonance system can use the automatic positioning function to scan the 3D positioning image, find the maximum level of the target part in the 3D layer, and segment the structure of the target part to determine the part boundary information corresponding to the target part.

[0068] As an optional embodiment of the present application, the automatic positioning function can be automatically positioned based on a deep learning target detection algorithm, and the position information of the target part can be obtained, so that the part boundary information corresponding to the target part can be obtained based on the position information.

[0069] As another optional embodiment of the present application, the automatic positioning function can be based on the segmentation algorithm of the convolutional neural network, automatically identify the position and shape of the target part and segment the structure of the target part, automatically place the FOV at the center of the scanned anatomical structure, and realize automatic positioning of the target part to obtain the part boundary information corresponding to the target part.

[0070] Taking the kidney as the target site as an example, the magnetic resonance system can use the automatic positioning function to scan the kidney 3D positioning image, find the largest level of the kidney in the 3D layer, and segment the kidney structure to determine the site boundary information corresponding to the kidney site.

[0071] Step S130: setting a shim frame according to the part boundary information.

[0072] The shimming frame is a frame used to plan the area for shimming operation.

[0073] The shim frame extends from the edge of the left region to the edge of the right region.

[0074] In a specific implementation, the magnetic resonance system can set the shim frame according to the part boundary information corresponding to the target part, so that the set shim frame can extend from the edge of the left area to the edge of the right area. Specifically, the magnetic resonance system can set the shim frame according to the left edge of the left area and the right edge of the right area, so that the set shim frame can extend from the left edge of the left area to the right edge of the right area, so that the set shim frame coverage area can not only include the target part body, but also include the artery and spine (the spine range includes vascular tissue) between the left area and the right area, so as to obtain more comprehensive information related to the target part.

[0075] Taking the target part as the kidney as an example, the set shim frame extends from the left edge of the left area to the right edge of the right area, so that the set shim frame coverage area can not only include the left and right kidney parts, but also include renal arteries, adrenal glands, spine (the spine range includes vascular tissue) and other parts and structures.

[0076] Step S140: performing a calibration operation in the area covered by the shim frame.

[0077] In a specific implementation, after setting the shimming frame, the magnetic resonance system can perform a calibration operation in the set shimming frame coverage area. Specifically, the magnetic resonance system can perform a shimming operation on the magnetic field (B0 magnetic field and B1 magnetic field) in the real space corresponding to the shimming frame coverage area.

[0078] In the above-mentioned magnetic resonance imaging scanning method, a positioning image of the detection object is obtained; part boundary information corresponding to the target part is identified in the positioning image; the target part includes a left area and a right area separated from each other; a shim frame is set according to the part boundary information; the shim frame extends from the edge of the left area to the edge of the right area; and a calibration operation is performed in the area covered by the shim frame.

[0079] In this way, by identifying the part boundary information corresponding to the target part in the positioning image of the detection object, the shape, position and size of the target part can be identified, so that the shimming frame is set according to the part boundary information, and the position placement and size of the shimming frame are automatically adjusted by using the shape, position and size of the target part, so that the set shimming frame extends from the edge of the left area of ​​the target part to the edge of the right area of ​​the target part, and can not only surround the target part body but also surround the artery, spine and other part structures between the left area and the right area of ​​the target part body, and not only can the shimming range be accurately determined, but also the information related to the target part can be more comprehensively obtained. And by performing the calibration operation in the set shimming frame coverage area, accurate shimming is achieved, the image quality of the scanning area where the target part is located is improved, and there is no need for the user to manually and repeatedly adjust the position and size of the shimming frame, the efficiency of the shimming operation is improved, and thus the intelligence of the shimming operation in the magnetic resonance imaging scanning process is effectively improved.

[0080] In one embodiment, setting a shim frame according to the part boundary information includes: adjusting an initial shim frame to surround a target part in the locator image according to the part boundary information to obtain a target shim frame.

[0081] The target shim frame extends from the edge of the left region to the edge of the right region.

[0082] The initial shim frame is an initially generated shim frame, and its position and size may be default parameters.

[0083] The method of adjusting the initial shim frame to surround the target part in the positioning image according to the part boundary information to obtain the target shim frame includes: adjusting the size and position of the initial shim frame according to the part boundary information; and obtaining the target shim frame when the adjusted initial shim frame surrounds the target part in the positioning image.

[0084] In a specific implementation, when the magnetic resonance system sets the shim frame according to the part boundary information, the magnetic resonance system can adjust the size and position of the initial shim frame according to the part boundary information. When the adjusted initial shim frame can surround the target part in the positioning image, the set shim frame can be obtained. The set shim frame can be used as the target shim frame, and the target shim frame can extend from the left edge of the left area to the right edge of the right area.

[0085] The size and position of the initial shim frame can be adjusted by scaling and moving the initial shim frame.

[0086] As an optional embodiment of the present application, the center point of the target shim frame may coincide with the center point of the target portion including the left area and the right area separated from each other.

[0087] The technical solution of this embodiment is to obtain a target shim frame by adjusting the initial shim frame to surround the target part in the positioning image according to the part boundary information. In this way, the shape, position and size of the target part can be determined according to the part boundary information, so that the target shim frame can be extended from the edge of the left area of ​​the target part to the edge of the right area of ​​the target part by adjusting the initial shim frame to surround the target part in the positioning image according to the part boundary information, so that the position and size of the shim frame can be adjusted according to the shape, position and size of the target part, the shim range can be accurately determined, and accurate shimming can be achieved in the shim coverage area, which is conducive to improving the image quality of the scanning area where the target part is located.

[0088] In one embodiment, when the adjusted initial shim frame surrounds the target part in the positioning image, a target shim frame is obtained, including: when the upper and lower boundaries of the adjusted initial shim frame and the distance between the upper and lower boundaries corresponding to the part boundary information, and when the left and right boundaries of the adjusted initial shim frame and the distance between the left and right boundaries corresponding to the part boundary information are less than a preset distance threshold, it is determined that the adjusted initial shim frame surrounds the target part in the positioning image.

[0089] The upper and lower boundaries corresponding to the part boundary information can be determined according to the uppermost boundary point and the lowermost boundary point among the boundary points constituting the boundary contour of the target part.

[0090] Considering that the positions of the left and right kidneys of different people may deviate, in one embodiment, the upper boundary point and the lower boundary point of the boundary contour of the target part may be determined by: inputting the positioning image into the trained first neural network model to obtain a simulated enhanced image;

[0091] Determine a first boundary contour and a second boundary contour of the target site from the simulated enhanced image, wherein the first boundary contour corresponds to the left kidney and the second boundary contour corresponds to the right kidney;

[0092] Determine a first upper boundary point and a first lower boundary point of the first boundary contour, and determine a second upper boundary point and a second lower boundary point of the second boundary contour;

[0093] The point closest to the upper edge between the first upper boundary point and the second upper boundary point is used as the upper boundary point of the boundary contour of the target part;

[0094] The point closest to the lower edge between the first lower boundary point and the second lower boundary point is used as the lower boundary point of the boundary contour of the target part.

[0095] Optionally, the first neural network model can be trained in the following way:

[0096] Acquire multiple sets of training images respectively, each set of training images includes a first image and a second image, wherein the first image is a kidney scan image without contrast agent injection, serving as a sample input image; the second image is an enhanced image obtained by performing kidney enhancement scanning after contrast agent injection, serving as a sample output image; the first image and the second image may correspond to the same physiological phase;

[0097] By inputting multiple sets of training images into the neural network model and adjusting the network parameters, the first neural network model can be obtained.

[0098] The left and right boundaries corresponding to the part boundary information can be determined based on the leftmost boundary point and the rightmost boundary point among the boundary points constituting the boundary contour of the target part. That is, they can be determined based on the leftmost boundary point in the part boundary information corresponding to the left region and the rightmost boundary point in the part boundary information corresponding to the right region.

[0099] In a specific implementation, when the adjusted initial shim frame surrounds the target part in the positioning image, the magnetic resonance system obtains the target shim frame. When the distance between the upper and lower boundaries of the adjusted initial shim frame and the upper and lower boundaries corresponding to the part boundary information, and when the distance between the left and right boundaries of the adjusted initial shim frame and the left and right boundaries corresponding to the part boundary information are both less than a preset distance threshold, the magnetic resonance system can determine that the adjusted initial shim frame surrounds the target part in the positioning image.

[0100] As an optional embodiment of the present application, since the smaller the shimming range is, the more accurate it is, and the image quality of the scanning area will be better, therefore, the magnetic resonance system can determine that the adjusted initial shimming frame is the target shimming frame when the adjusted initial shimming frame just surrounds the target part in the positioning image. Specifically, when the adjusted initial shimming frame is the minimum circumscribed frame corresponding to the target part, it is determined that the adjusted initial shimming frame just surrounds the target part in the positioning image. For example, when the shape of the shimming frame is a rectangle, when the adjusted initial shimming frame is the minimum circumscribed rectangle corresponding to the target part, it is determined that the adjusted initial shimming frame just surrounds the target part. In this way, the adjusted initial shimming frame that just surrounds the target part is used as the target shimming frame, which can minimize the shimming range to effectively improve the shimming accuracy.

[0101] The technical solution of this embodiment determines that the adjusted initial shim frame surrounds the target part in the locating image when the distance between the upper and lower boundaries of the adjusted initial shim frame and the upper and lower boundaries corresponding to the part boundary information, and when the distance between the left and right boundaries of the adjusted initial shim frame and the left and right boundaries corresponding to the part boundary information is less than a preset distance threshold. In this way, the size and position of the initial shim frame are adjusted based on the distance between the boundary of the adjusted initial shim frame and the boundary corresponding to the part boundary information, so that the position and size of the shim frame are automatically adjusted based on the position and size of the target part, so that the shim frame finally obtained can accurately surround the target part in the locating image, so that the shim range can be accurately determined to achieve accurate shimming.

[0102] In one embodiment, the method further includes: setting a pre-pulse module frame according to the part boundary information; the upper boundary of the pre-pulse module frame is aligned with the edge corresponding to the upper boundary point in the part boundary information; and performing a calibration operation in the coverage area of ​​the pre-pulse module frame.

[0103] The magnetic resonance imaging workflow includes not only the shimming workflow described in the above embodiment, but also a pre-pulse placement workflow.

[0104] The pre-pulse module frame is a border used to plan an area for placing the pre-pulse module.

[0105] The pre-pulse module may include an arterial blood vessel labeling module, an inversion recovery module, a saturation band module, etc., to suppress background signals such as fat signals and venous blood signals.

[0106] In a specific implementation, the magnetic resonance system can set a pre-pulse module frame in the pre-pulse placement workflow according to the site boundary information corresponding to the target site. Specifically, the magnetic resonance system can set the position of the pre-pulse module frame according to the upper boundary point of the boundary contour of the target site in the site boundary information, so that the upper boundary of the set pre-pulse module frame is flush with the edge corresponding to the upper boundary point. That is, the set pre-pulse module frame needs to be flush with the upper edge of the target site to reduce the suppression of the pre-pulse on the arterial input blood flow of the target site. For example, when the target site is the kidney site, the suppression of the pre-pulse on the renal arterial input blood flow can be reduced when the set pre-pulse module frame is flush with the upper edge of the kidney site.

[0107] Thus, after the pre-pulse module frame is set, the magnetic resonance system can perform a calibration operation in the set pre-pulse module frame coverage area. Specifically, the magnetic resonance system can calibrate the pulse signal of the real space corresponding to the pre-pulse module frame coverage area.

[0108] The technical solution of this embodiment is to set the pre-pulse module frame according to the part boundary information; the upper boundary of the pre-pulse module frame is flush with the edge corresponding to the upper boundary point in the part boundary information; and the calibration operation is performed in the coverage area of ​​the pre-pulse module frame. In this way, the position of the target part is used to automatically adjust the position of the pre-pulse module frame, so that the upper boundary of the set pre-pulse module frame is flush with the edge corresponding to the upper boundary point in the part boundary information, and the set pre-pulse module frame is kept flush with the upper edge of the target part, thereby reducing the suppression of the pre-pulse on the arterial input blood flow of the target part. And there is no need for the user to manually adjust the position of the pre-pulse module frame repeatedly, which improves the efficiency and accuracy of the pre-pulse module placement operation, and effectively improves the intelligence of the pre-pulse module placement operation during the magnetic resonance imaging scanning process.

[0109] In order to facilitate the understanding of those skilled in the art, Figure 2 A flowchart of a magnetic resonance imaging scanning method for the kidney area is provided. Figure 3 Provides a Figure 2 Schematic diagram of the process of matching magnetic resonance imaging scanning method for the kidney area.

[0110] like Figure 2 As shown, the magnetic resonance system can use the automatic positioning function to scan the 3D positioning image of the renal artery (kidney), find the largest level of the kidney in the 3D plane and segment the kidney structure. This automatic positioning function can automatically locate based on the deep learning target detection algorithm, and can obtain the part boundary information corresponding to the kidney part (including the upper, lower, left, right, front and back boundary information, which is the kidney contour position information), and calculate the size and position of the shim box based on the part boundary information.

[0111] The specific steps are as follows: according to the part boundary information identified in the kidney 3D positioning image, the maximum upper and lower long axis layers and the maximum left and right long axis layers of the kidney part are found, and according to the maximum upper and lower long axis layers and the maximum left and right long axis layers, the upper and lower boundaries and the left and right boundaries corresponding to the kidney part can be determined to adjust the left and right boundaries and the upper and lower boundaries of the shim frame, so that the shim frame is closely attached to the outer edges of the left and right kidney parts and covers the whole kidney, so as to further obtain a target shim frame that is closely attached to the kidney part (i.e., just surrounds the kidney part). In this way, the magnetic field (B0 magnetic field (main magnetic field) and B1 magnetic field (radio frequency field)) of the real space corresponding to the target shim frame coverage area can be shimmed to optimize the magnetic field of the real space corresponding to the target shim frame coverage area.

[0112] Similarly, the magnetic resonance system can adjust the pre-pulse module frame according to the site boundary information corresponding to the kidney site to obtain a target pre-pulse module frame surrounding the kidney site.

[0113] Among them, the schematic diagram of the kidney 3D positioning image, the part boundary information corresponding to the kidney part including the left area and the right area separated from each other in the kidney 3D positioning image, the target shim box and the pre-pulse module box can be seen in Figure 3 .

[0114] In this way, the shim frame and the pre-pulse module frame are automatically adjusted according to the part boundary information, so that the shim frame and the pre-pulse module frame can be automatically adjusted to surround the target part in the positioning image based on the size and position of the target part. There is no need for the user to manually adjust the placement of the shim frame and the pre-pulse module frame repeatedly, thereby reducing the scanning difficulty and scanning time, and effectively improving the intelligence and convenience of the overall workflow of magnetic resonance scanning.

[0115] In one embodiment, the method further includes: selecting a tomographic image that matches the site boundary information from the tomographic images corresponding to the target site as the target tomographic image; and obtaining a three-dimensional target site vascular morphology based on the target site artery boundary information segmented from each target tomographic image.

[0116] The tomographic image corresponding to the target part is an image obtained after a clinical scan of the target part. In an optional embodiment of the present application, the tomographic image corresponding to the target part can be an image obtained after a clinical scan of the target part after a calibration operation is performed on the shim frame coverage area and a calibration operation is performed on the pre-pulse module frame coverage area.

[0117] The target artery boundary information may be information used to characterize the boundary contour of the target artery, and may include position information of boundary points constituting the boundary contour of the target artery.

[0118] In a specific implementation, the magnetic resonance imaging workflow may also include an image post-processing (vascular segmentation) workflow after the tomographic images are obtained by clinical scanning. The tomographic images corresponding to the target part may include a series of images showing the target part through different sections. The magnetic resonance system may select the tomographic images that match the part boundary information corresponding to the target part from the tomographic images corresponding to the target part as the target tomographic images. In this way, the magnetic resonance system may obtain the three-dimensional target part vascular morphology based on the target part artery boundary information segmented from each target tomographic image.

[0119] For the convenience of understanding by those skilled in the art, taking the target site as the kidney as an example, Figure 4 A schematic diagram of the process of post-processing the tomographic images corresponding to the kidney area is provided. Figure 4As shown in the figure, after using the automatic positioning function to scan the 3D positioning image of the kidney and segmenting the boundary information of the kidney part, the kidney and renal artery can be marked along the outline of the kidney (i.e., the boundary information of the kidney part) in the tomographic image obtained by clinical scanning of the target part, and the abdominal aorta, renal artery and other blood vessels in the middle are retained, while the kidney is retained, and the acquisition image of the renal artery can be obtained. The deep learning target segmentation algorithm is used to learn the morphological characteristics of the kidney and renal blood vessels, and finally the input blood vessel image (the boundary information of the renal artery segmented in the target tomographic image corresponding to the kidney part) is obtained, and the output is the effect after cropping and MIP (Maximum Intensity Projection), and the three-dimensional renal blood vessel morphology is obtained.

[0120] Please refer to further Figure 4 , MRI scanning methods include:

[0121] Step 1: Obtain a positioning image of the detection object;

[0122] Step 2: Locate the left and right areas of the kidney in the positioning image;

[0123] Step three, according to the located left and right areas of the kidney, set a shim frame; perform shim calibration of the main magnetic field and the radio frequency field according to the shim frame; and, after the shim calibration, execute a scanning sequence to obtain an initial scanning result; optionally, a pre-pulse module may be inserted before the shim calibration and the scanning sequence are executed to suppress background signals such as fat signals and interference signals;

[0124] Step 4, automatically cropping the kidney region from the initial scan result;

[0125] Step 5: Perform MIP projection operation on the kidney region to obtain a renal artery vascular image. Compared with the existing kidney image that is manually outlined by doctors, this application improves the automation level of kidney region image processing.

[0126] For further reference, Figure 5 , provides a scanning sequence acquisition schematic diagram, such as Figure 5 As shown, the kidney acquisition performs multi-layer simultaneous interleaved scanning; each layer is scanned alternately and non-continuously. In this embodiment, within a repetition time (TR); the 1st, 3rd and 5th layers are acquired simultaneously, and each TR acquires a portion of the K-space data; the results of multiple TR acquisitions are used to obtain the scanning results of the 1st, 3rd and 5th layers; when scanning the 2nd, 4th and 6th layers, it is similar to the former. Acquiring multiple layers in one TR can reduce the acquisition time; interleaved acquisition of layers can reduce the crosstalk caused by the successive excitation of layers.

[0127] The technical solution of this embodiment is to select the tomographic images that match the part boundary information from the tomographic images corresponding to the target part as the target tomographic images; and obtain the three-dimensional target part vascular morphology according to the target part artery boundary information segmented from each target tomographic image. In this way, the target part artery boundary information can be accurately determined according to the part boundary information corresponding to the target part, so that the three-dimensional target part vascular morphology can be efficiently obtained according to the target part artery boundary information.

[0128] In another embodiment, Figure 6 As shown, a magnetic resonance imaging scanning method is provided, which is described by taking the application of the method to a magnetic resonance system as an example, and includes the following steps:

[0129] Step S602: Acquire a positioning image of the detection object.

[0130] Step S604: identifying part boundary information corresponding to the target part in the positioning image.

[0131] Step S606: adjusting the size and position of the initial shim frame according to the part boundary information.

[0132] Step S608: When the adjusted initial shim frame surrounds the target part in the scout image, a target shim frame is obtained.

[0133] Step S610, setting a pre-pulse module frame according to the part boundary information.

[0134] Step S612: performing a calibration operation in the target shim frame coverage area.

[0135] Step S614, performing a calibration operation in the area covered by the pre-pulse module frame.

[0136] It should be noted that the specific definition of the above steps can refer to the specific definition of a magnetic resonance imaging scanning method mentioned above.

[0137] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0138] Based on the same inventive concept, the embodiment of the present application also provides a magnetic resonance imaging scanning device for implementing the magnetic resonance imaging scanning method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the one or more magnetic resonance imaging scanning device embodiments provided below can refer to the above limitations on a magnetic resonance imaging scanning method, and will not be repeated here.

[0139] In one embodiment, Figure 7 As shown, a magnetic resonance imaging scanning device is provided, including: an acquisition module 710, an identification module 720, a setting module 730 and an execution module 740, wherein:

[0140] The acquisition module 710 is used to acquire a positioning image of the detection object.

[0141] The identification module 720 is used to identify part boundary information corresponding to a target part in the positioning image; the target part includes a left area and a right area separated from each other.

[0142] The setting module 730 is used to set a shim frame according to the part boundary information; the shim frame extends from the edge of the left area to the edge of the right area.

[0143] The execution module 740 is used to perform a calibration operation in the area covered by the shim frame.

[0144] In one embodiment, the setting module 730 is specifically configured to adjust the initial shim frame to surround the target part in the positioning image according to the part boundary information to obtain a target shim frame; the target shim frame extends from the edge of the left area to the edge of the right area.

[0145] In one embodiment, the setting module 730 is specifically configured to adjust the size and position of the initial shim frame according to the part boundary information; when the adjusted initial shim frame surrounds the target part in the scout image, the target shim frame is obtained.

[0146] In one embodiment, the setting module 730 is specifically used to determine that the adjusted initial shim frame surrounds the target part in the positioning image when the distance between the upper and lower boundaries of the adjusted initial shim frame and the upper and lower boundaries corresponding to the part boundary information, and when the distance between the left and right boundaries of the adjusted initial shim frame and the left and right boundaries corresponding to the part boundary information is less than a preset distance threshold.

[0147] In one of the embodiments, the device also includes: a pre-pulse setting module, used to set a pre-pulse module frame according to the part boundary information; the upper boundary of the pre-pulse module frame is flush with the edge corresponding to the upper boundary point in the part boundary information; and a calibration operation is performed in the coverage area of ​​the pre-pulse module frame.

[0148] In one of the embodiments, the device also includes: an image post-processing module, which is used to screen out tomographic images that match the boundary information of the target part from the tomographic images corresponding to the target part, as target tomographic images; and obtain the three-dimensional target part vascular morphology based on the target part artery boundary information segmented from each of the target tomographic images.

[0149] Each module in the above-mentioned magnetic resonance imaging scanning device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0150] In one embodiment, a computer device is provided. The computer device may be a computer device in a magnetic resonance system. The internal structure diagram thereof may be as follows: Figure 8 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. 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 input / output interface of the computer device is used to exchange information between the processor and an external device. 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 mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a magnetic resonance imaging scanning method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen 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, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0151] Those skilled in the art will understand that Figure 8The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0152] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0153] 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 steps in the above-mentioned method embodiments are implemented.

[0154] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0155] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0156] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and 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 embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present 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), magnetoresistive 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. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0157] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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.

[0158] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A magnetic resonance imaging scanning method, characterized in that: The method comprises: Acquire a positioning image of the detection object; Identifying part boundary information corresponding to a target part in the positioning image; the target part includes a left area and a right area separated from each other; According to the part boundary information, a shim frame is set; the shim frame extends from an edge of the left area to an edge of the right area; A calibration operation is performed in the area covered by the shim frame.

2. The method according to claim 1, characterized in that The step of setting a shim frame according to the part boundary information includes: According to the part boundary information, an initial shim frame is adjusted to surround the target part in the scout image to obtain a target shim frame; the target shim frame extends from the edge of the left area to the edge of the right area.

3. The method according to claim 2, characterized in that The step of adjusting the initial shim frame to surround the target part in the scout image according to the part boundary information to obtain a target shim frame includes: According to the part boundary information, adjusting the size and position of the initial shim frame; When the adjusted initial shim frame surrounds the target part in the scout image, the target shim frame is obtained.

4. The method according to claim 3, characterized in that When the adjusted initial shim frame surrounds the target part in the scout image, the target shim frame is obtained, comprising: When the distance between the upper and lower boundaries of the adjusted initial shim frame and the upper and lower boundaries corresponding to the part boundary information, and when the distance between the left and right boundaries of the adjusted initial shim frame and the left and right boundaries corresponding to the part boundary information is less than a preset distance threshold, it is determined that the adjusted initial shim frame surrounds the target part in the positioning image.

5. The method according to claim 1, characterized in that The method further comprises: According to the part boundary information, a pre-pulse module frame is set; the upper boundary of the pre-pulse module frame is flush with the edge corresponding to the upper boundary point in the part boundary information; A calibration operation is performed in the pre-pulse module frame coverage area.

6. The method according to claim 1, characterized in that The method further comprises: Screening out, from the tomographic images corresponding to the target part, a tomographic image matching the boundary information of the part as a target tomographic image; The three-dimensional target part blood vessel morphology is obtained according to the target part artery boundary information segmented from each of the target tomographic images.

7. A magnetic resonance imaging scanning device, characterized in that: The device comprises: An acquisition module, used for acquiring a positioning image of the detection object; An identification module, used for identifying part boundary information corresponding to a target part in the positioning image; the target part includes a left area and a right area separated from each other; A setting module, configured to set a shim frame according to the part boundary information; the shim frame extends from an edge of the left region to an edge of the right region; An execution module is used to perform a calibration operation in the area covered by the shim frame.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images