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

Abstract

The present application relates to a magnetic resonance scanning method, apparatus, computer device, and storage medium. The method includes: performing magnetic resonance scanning on at least one slice group of the heart of a scanning object within an initial cardiac cycle to obtain an initial cardiac localization; determining a scanning orientation for the next cardiac cycle according to the initial cardiac localization; the initial cardiac cycle and the next cardiac cycle being within one breath-hold range of the scanning object; and performing scanning on at least one slice group according to the scanning orientation to obtain an orientation image of the cardiac anatomical structure. Using this method can greatly reduce the breath-holding time of the patient, shorten the scanning time, and at the same time ensure the localization effect required by the original localization.

Description

Technical Field

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

[0002] With the development of magnetic resonance imaging technology, magnetic resonance imaging, as a non-invasive early diagnosis method, has been widely used clinically.

[0003] Generally, the magnetic resonance scanning process can be generally divided into two stages: a scanning and positioning stage and a scanning and examination sequence stage. Among them, the scanning and positioning stage mainly provides a general anatomical structure and relative spatial position, and the obtained images have low resolution and poor contrast; the examination sequence stage can provide magnetic resonance images with better contrast and resolution for doctors to examine compared with the scanning and positioning stage. Usually, the scanning and examination sequence stage performs breath-hold scanning, so the scanning and positioning stage also selects breath-hold scanning to ensure that the relative position of the heart in the positioning image and the actual imaging sequence scan is consistent.

[0004] However, the traditional cardiac magnetic resonance positioning scanning method requires the patient to hold their breath multiple times. Generally, it requires five breaths. The first breath is used to scan the initial transverse, coronal, and sagittal planes; based on the scanning results of the first breath, the position of the interventricular septum is manually determined, and the second breath is used for transverse plane scanning; based on the transverse plane results of the second breath, it is manually confirmed to be parallel to the interventricular septum, and the third breath is used for two-chamber heart structure scanning; based on the two-chamber heart image of the third breath, the scanning orientation of the long-axis four-chamber heart is determined, and the fourth breath-hold scan is performed; based on the fourth long-axis image, the short-axis orientation is positioned, and the fifth breath is used for short-axis orientation scanning. Through the above five breath-holds, anatomical two-chamber heart, four-chamber heart, and short-axis positioning images can be roughly obtained, and the clinical examination sequence can be scanned based on these positioning images. The positioning scanning time is relatively long, and if anatomical positions such as true four-chamber heart and three-chamber heart need to be positioned, the positioning scanning time will be further prolonged. Summary of the Invention

[0005] Based on this, it is necessary to provide a magnetic resonance scanning method, device, computer device, and storage medium that can reduce the scanning time for the above technical problems.

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

[0007] During an initial cardiac cycle, perform magnetic resonance scanning on at least one slice group of the heart of the scanning object to obtain an initial cardiac positioning;

[0008] According to the initial cardiac positioning, determine the scanning orientation of the next cardiac cycle; the initial cardiac cycle and the next cardiac cycle are within a single breath-hold range of the scanning object;

[0009] According to the scanning orientation, scan the at least one slice group to obtain an orientation image of the cardiac anatomy.

[0010] In one embodiment, the determining the scanning orientation of the next cardiac cycle according to the initial cardiac positioning includes:

[0011] According to the initial cardiac positioning, obtain an initial cardiac positioning image;

[0012] According to the initial cardiac positioning image, determine the scanning orientation of the next cardiac cycle.

[0013] In one embodiment, the determining the scanning orientation of the next cardiac cycle according to the initial cardiac positioning image includes:

[0014] Input the initial cardiac positioning image into a preset deep learning network model, and through the deep learning network model, obtain the scanning orientation of the next cardiac cycle.

[0015] In one embodiment, before scanning at least one slice group of the heart of the scanned object in the initial cardiac cycle to obtain an initial cardiac positioning image, the method further includes:

[0016] Adjust the magnetic resonance scanning protocol to a multi-slice group protocol.

[0017] In one embodiment, the scanning orientation includes at least one of a transverse plane, a coronal plane or a sagittal plane.

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

[0019] Use the orientation image of the cardiac anatomy to perform imaging scanning on the heart of the scanned object to obtain cardiac magnetic resonance data of the scanned object;

[0020] Use a reconstruction algorithm to reconstruct the cardiac magnetic resonance data to obtain a cardiac magnetic resonance image of the scanned object.

[0021] In one embodiment, the reconstruction algorithm includes a Fourier transform algorithm, a compressed sensing algorithm or a parallel reconstruction algorithm.

[0022] A magnetic resonance scanning device, the device includes:

[0023] A first scanning module, configured to perform magnetic resonance scanning on at least one slice group of the heart of a scanned object in an initial cardiac cycle to obtain an initial cardiac positioning;

[0024] A determination module, configured to determine a scanning orientation for the next cardiac cycle according to the initial cardiac localization; the initial cardiac cycle and the next cardiac cycle are within one breath-hold range of the scanned object;

[0025] A second scanning module, configured to scan the at least one slice group according to the scanning orientation to obtain an orientation image of the cardiac anatomical structure.

[0026] A computer device, comprising a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0027] During an initial cardiac cycle, perform magnetic resonance scanning on at least one slice group of the heart of the scanned object to obtain an initial cardiac localization;

[0028] According to the initial cardiac localization, determine a scanning orientation for the next cardiac cycle; the initial cardiac cycle and the next cardiac cycle are within one breath-hold range of the scanned object;

[0029] According to the scanning orientation, scan the at least one slice group to obtain an orientation image of the cardiac anatomical structure.

[0030] A computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0031] During an initial cardiac cycle, perform magnetic resonance scanning on at least one slice group of the heart of the scanned object to obtain an initial cardiac localization;

[0032] According to the initial cardiac localization, determine a scanning orientation for the next cardiac cycle; the initial cardiac cycle and the next cardiac cycle are within one breath-hold range of the scanned object;

[0033] According to the scanning orientation, scan the at least one slice group to obtain an orientation image of the cardiac anatomical structure.

[0034] The above-mentioned magnetic resonance scanning method, device, computer device, and storage medium can obtain an initial heart localization by performing magnetic resonance scanning on at least one slice group of the heart of the scanned object within the initial cardiac cycle. Thus, the scanning orientation for the next cardiac cycle can be determined based on the initial heart localization. Furthermore, at least one slice group of the heart of the scanned object can be scanned according to the determined scanning orientation for the next cardiac cycle to obtain an orientation image of the cardiac anatomical structure. Since magnetic resonance scanning is performed on at least one slice group of the heart of the scanned object within the initial cardiac cycle, and the initial cardiac cycle and the next cardiac cycle are within one breath-hold range of the scanned object, by completing the positioning of multiple slice groups within the same breath-hold, the breath-hold time of the patient can be significantly reduced, the scanning time can be shortened, and at the same time, the positioning effect required by the original positioning can be ensured. Brief Description of the Drawings

[0035] Figure 1 It is an application environment diagram of the magnetic resonance scanning method in an embodiment;

[0036] Figure 2 It is a schematic flowchart of the magnetic resonance scanning method in an embodiment;

[0037] Figure 3 It is a schematic flowchart of the magnetic resonance scanning method in another embodiment;

[0038] Figure 3a It is a schematic diagram of heart localization in an embodiment;

[0039] Figure 3b It is a schematic structural diagram of a deep learning network model in an embodiment;

[0040] Figure 4 It is a schematic flowchart of the magnetic resonance scanning method in another embodiment;

[0041] Figure 5 It is a schematic diagram of a cardiac scan image scanned according to the result of manual localization in the initial cardiac cycle in an embodiment;

[0042] Figure 6 It is a cardiac scan image scanned according to the result of localization obtained based on a trained network in an embodiment;

[0043] Figure 7 It is a schematic diagram of a rectangular coordinate system established in an embodiment;

[0044] Figure 8 It is a schematic diagram of the intersection line segment and perpendicular line between the slice to be localized and the current slice in an embodiment;

[0045] Figure 9 It is a schematic diagram of the processed image of the localization image in an embodiment;

[0046] Figure 10 Schematic diagram of the process of cardiac scanning in one embodiment;

[0047] Figure 11 Block diagram of the structure of a magnetic resonance scanning device in one embodiment;

[0048] Figure 12 Internal structure diagram of a computer device in one embodiment. Detailed implementation manners

[0049] In order to make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0050] The magnetic resonance scanning method provided by the embodiments of the present application can be applicable to a magnetic resonance device as shown in Figure 1 . The magnetic resonance device includes a processor and a memory connected through a system bus. A computer program is stored in the memory. When the processor executes the computer program, it can execute the steps of the following method embodiments. Optionally, the magnetic resonance device may further include a network interface, a display screen, and an input device. Among them, the processor of the magnetic resonance device is used to provide computing and control capabilities. The memory of the magnetic resonance device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. Optionally, the magnetic resonance device may be a server, a personal computer, a personal digital assistant, or other terminal devices, such as a tablet computer, a mobile phone, etc., or may be a cloud or a remote server. The specific form of the magnetic resonance device is not limited in the embodiments of the present application.

[0051] In one embodiment, as shown in Figure 2 , a magnetic resonance scanning method is provided. Taking the method applied to the magnetic resonance device in Figure 1 as an example, the method includes the following steps:

[0052] S201, during an initial cardiac cycle, perform magnetic resonance scanning on at least one slice group of the heart of the scanned object to obtain an initial cardiac localization.

[0053] Among them, during the process of scanning the heart of the scanned object, the scanned object needs to hold its breath for scanning. The initial cardiac cycle is the time interval when the scanned object holds its first breath.

[0054] Specifically, during the same breath-hold, in the previous / initial cardiac cycle (i.e., the initial cardiac cycle), the magnetic resonance device performs magnetic resonance scanning on at least one slice group of the scanned object's heart to obtain the initial cardiac localization of the scanned object. It should be noted that in the traditional technology, during the time interval of a single breath-hold of the scanned object, the magnetic resonance scanning performed by the magnetic resonance device on the scanned object's heart only scans a single scanning orientation of one slice group of the scanned object's heart. However, in this application, during the time interval of the scanned object's breath-hold, the magnetic resonance scanning performed by the magnetic resonance device on the scanned object's heart is to perform scans on multiple slice groups within a single breath-hold. The multiple slice groups can correspond to different scanning orientations of the same scanning area, thereby shortening the breath-hold time of the scanned object and reducing the time of magnetic resonance scanning. It can be understood that the initial cardiac localization here includes the general outline and relative position of the scanned object's heart.

[0055] S202. Determine the scanning orientation of the next cardiac cycle according to the initial cardiac localization; the initial cardiac cycle and the next cardiac cycle are within the range of a single breath-hold of the scanned object.

[0056] Specifically, the magnetic resonance device determines the scanning orientation of the next cardiac cycle according to the obtained initial cardiac localization. Among them, the above-mentioned initial cardiac cycle and the above-mentioned next cardiac cycle are within the range of a single breath-hold of the scanned object. Optionally, the magnetic resonance device can determine the scanning orientation of the next cardiac cycle according to the outline of the heart and the positions of the atria and ventricles in the initial cardiac localization. It can be understood that the magnetic resonance device determines the scanning orientation of the next cardiac cycle during the time interval after obtaining the initial cardiac localization and before starting the scanning of the next cardiac cycle.

[0057] S203. Scan at least one slice group according to the scanning orientation to obtain an orientation image of the cardiac anatomy.

[0058] Specifically, the magnetic resonance device scans at least one slice group according to the determined scanning orientation of the next cardiac cycle to obtain an orientation image of the cardiac anatomy. It should be noted that the obtained orientation image of the cardiac anatomy is an orientation image of the cardiac anatomy obtained by determining the scanning orientation through multiple adjustments of the scanning orientation and using this scanning orientation to scan at least one slice group of the scanned object. Considering that only one slice group is scanned in each cardiac cycle, in the embodiments of this application, before the scanning of the next cardiac cycle is executed, the size of the FOV can also be adjusted according to the determined scanning orientation so that the adjusted FOV is adapted to the range of the slice group of the next cardiac cycle, that is, the scanning of each cardiac cycle can adapt to the size of the determined slice group, avoiding aliasing artifacts caused by unreasonable FOV settings.

[0059] In the above magnetic resonance scanning method, since magnetic resonance scanning is performed on at least one slice group of the heart of the scanned object in the initial cardiac cycle, and the initial cardiac cycle and the next cardiac cycle are within the range of a single breath-hold of the scanned object, by positioning and placing multiple slice groups within the same breath-hold, the breath-hold time of the patient can be greatly reduced, the scanning time can be shortened, and at the same time, the positioning effect required for the original positioning can be ensured.

[0060] In the scenario of determining the scanning orientation of the next cardiac cycle based on the initial cardiac localization image above, in one embodiment, as Figure 3 shown, the above S202 includes:

[0061] S301, obtain the initial cardiac localization image according to the initial cardiac localization.

[0062] Specifically, the magnetic resonance device obtains the initial cardiac localization image according to the obtained initial cardiac localization above. Optionally, the magnetic resonance device can perform image reconstruction on the magnetic resonance data corresponding to the obtained initial cardiac localization to obtain the initial cardiac localization image.

[0063] S302, determine the scanning orientation of the next cardiac cycle according to the initial cardiac localization image.

[0064] Specifically, the magnetic resonance device determines the scanning orientation of the next cardiac cycle according to the obtained initial cardiac localization image.

[0065] As Figure 3a shown is a schematic diagram of cardiac localization in an embodiment of the present application. It includes four cardiac cycles s1 - s4, and within each cardiac cycle, positioning scans of different slice groups of the same cardiac region are performed. Specifically, taking the cardiac cycle s1 as the first cardiac cycle or the initial cardiac cycle, a first positioning scan sequence is performed within s1, and after reconstruction, a first slice group image can be obtained; after processing the first slice group image, a first decision instruction can be generated, and this first decision instruction acts on the positioning instruction of the second cardiac cycle s2 to generate a second positioning scan sequence. And so on, the positioning signal of the second cardiac cycle s2 can act on the positioning instruction of the third cardiac cycle s3 after reconstruction and decision-making operations, and the positioning signal of the third cardiac cycle s3 can act on the positioning instruction of the fourth cardiac cycle s4 after reconstruction and decision-making operations.

[0066] Optionally, the magnetic resonance device inputs the above initial cardiac localization image into a preset deep learning network model, and through this deep learning network model, obtains the scanning orientation of the next cardiac cycle. Exemplarily, the constructed deep learning network structure can be as Figure 3bAs shown, optionally, a batch of anatomical orientation images such as transverse septum images, two-chamber images, four-chamber images, short-axis images, and three-chamber images of approximately 200 people can be collected in advance. According to the actual scanning process, the initial deep learning network is trained. Optionally, the training mode of the initial deep learning network can be divided into the following four cases: In the first case, the input is a transverse image, and the output is the two-chamber orientation; in the second case, the input is a two-chamber image, and the output is the four-chamber image orientation; in the third case, the input is a four-chamber image, and the output is the short-axis image orientation; in the fourth case, the input is a four-chamber image and a short-axis image, and the output is a three-chamber image, etc. The initial deep learning network is trained using such training modes. Of course, the deep learning network model can include multiple initial deep learning networks respectively processed by the foregoing combined training modes.

[0067] In this embodiment, the magnetic resonance device can quickly obtain an initial cardiac localization image based on the initial cardiac localization, so that the scanning orientation of the next cardiac cycle can be quickly determined according to the obtained initial cardiac localization image, improving the efficiency of determining the scanning orientation of the next cardiac cycle, and thus shortening the scanning time for magnetic resonance scanning of the scanned object. Compared with the prior art methods of automatically detecting the characteristic parts of the heart based on multiple sectional image data or acquiring whole-heart images during a single breath-hold, in this application, only the localization images of one slice group are acquired within one cardiac cycle, which can avoid the problem of too low image resolution caused by too small FOV due to simultaneous scanning of multiple layers of images during whole-heart scanning. Moreover, cardiac localization can be completed during a single breath-hold, avoiding repeated operations by the operator.

[0068] In the scenario of scanning at least one slice group of the heart of the scanned object within the initial cardiac cycle of the scanned object, in one embodiment, before the above S201, the method further includes: adjusting the magnetic resonance scanning protocol to a multi-slice group protocol.

[0069] Specifically, before the magnetic resonance device scans at least one slice group of the heart of the scanned object within the previous cardiac cycle during the same breath-hold, the magnetic resonance device adjusts its corresponding magnetic resonance scanning protocol to a multi-slice group protocol, that is, adjusts the scanning mode of the magnetic resonance device so that it can scan multiple slice groups of the heart of the scanned object within a single breath-hold of the scanned object. Optionally, when the magnetic resonance device scans the heart of the scanned object, its corresponding scanning orientations include transverse, coronal, and sagittal.

[0070] In this embodiment, the magnetic resonance device adjusts the magnetic resonance scanning protocol to a multi-slice group protocol, which enables the magnetic resonance device to perform multi-slice group scanning on the heart of the scanned object, and can complete the positioning of multiple slice groups within the same breath-hold, reducing the breath-hold time of the scanned object, and thus reducing the scanning time for the scanned object.

[0071] In the scenario where the above-mentioned magnetic resonance device determines the target cardiac localization image of the scanned object, the magnetic resonance device can perform a scan of the examination sequence on the heart of the scanned object based on the determined localization image to obtain the cardiac magnetic resonance image of the scanned object. In one embodiment, as Figure 4 shown, the above method further includes:

[0072] S401, using the orientation image of the cardiac anatomical structure, perform an imaging scan on the heart of the scanned object to obtain the cardiac magnetic resonance data of the scanned object.

[0073] Specifically, the magnetic resonance device uses the obtained orientation image of the cardiac anatomical structure to perform an imaging scan on the heart of the scanned object to obtain the cardiac magnetic resonance data of the scanned object. It should be noted that the imaging scan performed on the heart of the scanned object here is an imaging scan of at least one slice group of the heart of the scanned object. Optionally, the magnetic resonance device can obtain the corresponding scan orientation, the contour of the heart of the scanned object, and the relative position of the heart of the scanned object according to the target cardiac localization image, and perform an imaging scan on the heart of the scanned object to obtain the cardiac magnetic resonance data of the scanned object.

[0074] S402, use a reconstruction algorithm to reconstruct the cardiac magnetic resonance data to obtain the cardiac magnetic resonance image of the scanned object.

[0075] Specifically, the magnetic resonance device uses a reconstruction algorithm to reconstruct the cardiac magnetic resonance data of the scanned object to obtain the cardiac magnetic resonance image of the scanned object. Optionally, the above reconstruction algorithm includes a Fourier transform algorithm, a compressed sensing algorithm, and a parallel reconstruction algorithm. Optionally, before the magnetic resonance device uses the reconstruction algorithm to reconstruct the cardiac magnetic resonance data, it can preprocess the obtained cardiac magnetic resonance data, and use the processed cardiac magnetic resonance data for reconstruction to obtain the cardiac magnetic resonance image of the scanned object.

[0076] In this embodiment, the magnetic resonance device can use the target cardiac localization image to quickly perform an imaging scan on the heart of the scanned object, quickly obtain the cardiac magnetic resonance data of the scanned object, so that the obtained cardiac magnetic resonance data can be quickly reconstructed using the reconstruction algorithm, and the cardiac magnetic resonance image of the scanned object can be quickly obtained, improving the efficiency of obtaining the cardiac magnetic resonance image of the scanned object and reducing the scanning time of the scanned object.

[0077] The following takes a specific magnetic resonance scanning method as an example for illustration. The above magnetic resonance scanning method may include the following steps: First, within the initial cardiac cycle, perform a magnetic resonance scan on at least one slice group of the heart of the scanned object to obtain an initial cardiac localization image. In one embodiment, the cardiac scan image scanned according to the result of manual localization in the initial cardiac cycle can be as Figure 5As shown, the cardiac scan image obtained from the initial cardiac cycle scan is a transverse image. The initial localization result of the cardiac scan image obtained from the initial cardiac cycle scan based on the deep learning network model can be as Figure 6 shown, where Figure 6 the coordinate points marked in Figure 6 are the difference points. Take the white long line segment in Figure 7 as LA, and take the white short line segment as LB. Establish a rectangular coordinate system as shown in a at the lower left corner of the cardiac scan image. Let the coordinates of the points on the LA line segment be {(x a )}, and obtain the set of all points on the coil LA line. Assume the equation of the LA line segment is y = ax + b. From the existing point coordinates {(x a , y a )} set on the LA line segment above, use the least squares method to fit and obtain the equation of the LA line segment, that is, find the minimum case to obtain the values of a and b. According to the obtained values of a and b, obtain the equation of y = ax + b. Then take the intersection point parallel to the LA line segment and the LB line segment, draw a perpendicular line to the LA line segment through the intersection point, take the midpoint of the perpendicular line, and then draw a line segment C (y = ax + c) parallel to the equation of the LA line segment through the midpoint. The line segment C is the intersection line of the to-be-localized slice and the current slice. The to-be-localized slice can be determined according to the equation of the intersection line C, so as to obtain the initial cardiac localization. Among them, the schematic diagram of the line segment C and the perpendicular line is as Figure 8 shown. Then, according to the initial cardiac localization image, determine the scanning orientation of the subsequent cardiac cycles of the initial cardiac cycle. One or more subsequent cardiac cycles and the initial cardiac cycle are all within the range of one breath-hold of the scanning object.

[0078] Furthermore, in this embodiment, the slice position calculated according to the above steps can be added to the original slice position. Assume that the original slice position determination method is determined by the normal vector V(x, y, z) and the point coordinates N(x, y, z) on the plane, then update the corresponding coordinate information and recalculate the radio frequency, gradient, and modem information. Usually, there will be a next cardiac cycle during use. The situation of multi-layer cardiac cycle information described above can be utilized. For example, as Figure 9 shown in the localization image of the true two-chamber heart (the localization image collected in the sixth cardiac cycle / sixth heartbeat in the figure), the short-axis localization image (the localization image collected in the fifth cardiac cycle / fifth heartbeat in the figure) and the pseudo two-chamber localization image (the localization image collected in the third cardiac cycle / third heartbeat in the figure) result information are required.

[0079] In one embodiment, the magnetic resonance scanning method can achieve automatic localization scanning of the heart. The method includes:

[0080] First, within the initial cardiac cycle / the first cardiac cycle, perform magnetic resonance scanning on at least one slice group of the scanned object's heart to obtain a first set of images. In this embodiment, the scanning orientation within the initial cardiac cycle is a transverse plane as shown in Figure 5 as shown.

[0081] Second, process the first set of images to obtain feature points. In this embodiment, the aforementioned deep learning network model can be used to process the first set of images to obtain difference points as shown in Figure 6 as shown, and LA and LB are the feature points.

[0082] Third, determine a positioning scan sequence for one cardiac cycle or multiple cardiac cycles after the initial cardiac cycle based on the feature points, and this one cardiac cycle or multiple cardiac cycles belong to the same breath-hold range. Optionally, based on the feature points, the scan slices / scan orientations for this one cardiac cycle or multiple cardiac cycles can be determined, and a feedback execution can be generated according to the determined scan slices / scan orientations. The processor can generate a positioning scan sequence for one cardiac cycle or multiple cardiac cycles based on this feedback instruction. In this embodiment, determining a positioning scan sequence for one cardiac cycle or multiple cardiac cycles after the initial cardiac cycle based on the feature points can include: determining a rotation matrix based on the feature points, and this rotation matrix includes radiofrequency pulse parameters, gradient pulse parameters, center frequency parameters of the modem, FOV parameters, etc.; determining a positioning scan sequence for one cardiac cycle or multiple cardiac cycles based on the rotation matrix.

[0083] Then, execute a positioning scan sequence for one cardiac cycle or multiple cardiac cycles to determine the orientation image / imaging orientation of the cardiac anatomy.

[0084] Finally, use the orientation image of the cardiac anatomy to perform imaging scanning on the scanned object's heart to obtain the cardiac magnetic resonance data of the scanned object.

[0085] According to the initial cardiac positioning, the positioning scan orientation for subsequent cardiac cycles can be determined, where the initial cardiac cycle and the subsequent cardiac cycles are within one breath-hold range of the scanned object (the interval between two peaks of the electrocardiogram waveform in the figure is one cardiac cycle). In this embodiment, as shown in Figure 10As shown, the initial cardiac cycle is a pseudo two-chamber (2ch) acquisition. Through the reconstruction module, a 2ch image can be obtained. The 2ch image can be processed by the acquisition module to extract the first feature point. The first feature point is sent to the control module to determine the first slice reference information of the subsequent cardiac cycles of the current cardiac cycle, corresponding to the first feedback instruction, that is, used to determine the scanning slice / scanning orientation of the subsequent cardiac cycles. Similarly, after the 2ch acquisition, a short-axis (sax) acquisition can be performed. Through the reconstruction module, a sax image can be obtained. The image can be processed by the acquisition module to extract the second feature point. The second feature point is sent to the control module to determine the second slice reference information of the subsequent cardiac cycles of the current cardiac cycle, corresponding to the second feedback instruction. Further, the control module generates a positioning scan sequence for true two-chamber (2ch) acquisition according to the corresponding first feedback instruction and second feedback instruction. The positioning scan sequence includes the scanning orientation and pulse parameters.

[0086] In one embodiment, the control module generating the scan sequence for true two-chamber acquisition according to the corresponding first feedback instruction and second feedback instruction may include: determining the scanning slice / scanning orientation corresponding to the true two-chamber according to the corresponding first feedback instruction and second feedback instruction; calculating the estimated radiofrequency energy for executing the pre-set true two-chamber positioning scan sequence; estimating whether the execution of the pre-set true two-chamber positioning scan sequence will cause the specific absorption ratio (SAR) to exceed the set threshold according to the estimated radiofrequency energy, the radiofrequency energy of the pseudo two-chamber acquisition, and the radiofrequency energy of the short-axis acquisition. When the SAR exceeds the set threshold, adjusting the radiofrequency parameters of the pre-set true two-chamber positioning scan sequence to generate the pulse parameters of the positioning scan sequence for true two-chamber acquisition. Optionally, the radiofrequency energy of the pseudo two-chamber acquisition and the radiofrequency energy of the short-axis acquisition can be obtained by real-time detection or simulated using a theoretical model. In this embodiment, by adjusting the radiofrequency parameters of the pre-set true two-chamber positioning scan sequence, it can be ensured that the execution of the pulse sequence within one breath-hold range will not cause the radiofrequency energy absorbed by the detection object to exceed the safe range, ensuring the safety of the detection object.

[0087] It should be understood that although Figure 2-10 the steps in the flowchart of Figure 2-10At least a part of the steps may include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same moment, but can be executed at different moments. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0088] In one embodiment, as Figure 11 shown, a magnetic resonance scanning device is provided, including: a first scanning module, a determination module, and a second scanning module, where:

[0089] The first scanning module is configured to perform magnetic resonance scanning on at least one slice group of the heart of a scanned object during an initial cardiac cycle to obtain an initial cardiac localization.

[0090] The determination module is configured to determine a scanning orientation for the next cardiac cycle according to the initial cardiac localization; the initial cardiac cycle and the next cardiac cycle are within one breath-hold range of the scanned object.

[0091] The second scanning module is configured to scan a plurality of slice groups according to the scanning orientation to obtain an orientation image of the cardiac anatomical structure.

[0092] Optionally, the scanning orientation includes a transverse plane, a coronal plane, and a sagittal plane.

[0093] The magnetic resonance scanning device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here.

[0094] Based on the above embodiment, optionally, the above determination module includes: a first determination unit and a second determination unit, where:

[0095] The first determination unit is configured to obtain an initial cardiac localization image according to the initial cardiac localization.

[0096] The second determination unit is configured to determine the scanning orientation for the next cardiac cycle according to the initial cardiac localization image.

[0097] The magnetic resonance scanning device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here.

[0098] Based on the above embodiment, optionally, the above second determination unit is specifically configured to input the initial cardiac localization image into a preset deep learning network model, and obtain the scanning orientation for the next cardiac cycle through the deep learning network model.

[0099] The magnetic resonance scanning device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here.

[0100] Based on the above embodiments, optionally, the above device further includes: an adjustment module, where:

[0101] The adjustment module is configured to adjust the magnetic resonance scanning protocol to a multi-slice group protocol.

[0102] The magnetic resonance scanning device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effects are similar, which will not be elaborated here.

[0103] Based on the above embodiments, optionally, the above device further includes: a third scanning module and an acquisition module, where:

[0104] The third scanning module is configured to perform imaging scanning on the heart of the scanned object by using the orientation image of the heart anatomical structure to obtain the cardiac magnetic resonance data of the scanned object.

[0105] The acquisition module is configured to reconstruct the cardiac magnetic resonance data by using a reconstruction algorithm to obtain the cardiac magnetic resonance image of the scanned object.

[0106] Optionally, the reconstruction algorithms include Fourier transform algorithm, compressed sensing algorithm, and parallel reconstruction algorithm.

[0107] The magnetic resonance scanning device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effects are similar, which will not be elaborated here.

[0108] For the specific limitations of the magnetic resonance scanning device, reference can be made to the limitations on the magnetic resonance scanning method in the above text, which will not be elaborated here. Each module in the above magnetic resonance scanning device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0109] In one embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 12 shown. The computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store cardiac magnetic resonance data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a magnetic resonance scanning method.

[0110] Those skilled in the art can understand that Figure 12 the structure shown in

[0111] is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0112] In an initial cardiac cycle, perform magnetic resonance scanning on at least one slice group of the heart of the scanned object to obtain an initial cardiac localization;

[0113] According to the initial cardiac localization, determine the scanning orientation of the next cardiac cycle; the initial cardiac cycle and the next cardiac cycle are within one breath-hold range of the scanned object;

[0114] According to the scanning orientation, scan at least one slice group to obtain an orientation image of the cardiac anatomical structure.

[0115] For the computer device provided in the above embodiment, its implementation principle and technical effects are similar to those of the above method embodiment, and will not be elaborated here.

[0116] In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0117] In an initial cardiac cycle, perform magnetic resonance scanning on at least one slice group of the heart of the scanned object to obtain an initial cardiac localization;

[0118] According to the initial cardiac localization, determine the scanning orientation of the next cardiac cycle; the initial cardiac cycle and the next cardiac cycle are within one breath-hold range of the scanned object;

[0119] According to the scanning orientation, scan at least one slice group to obtain an orientation image of the cardiac anatomical structure.

[0120] For the computer-readable storage medium provided in the above embodiment, its implementation principle and technical effects are similar to those of the above method embodiment, and will not be elaborated here.

[0121] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above various methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0122] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0123] The above-described embodiments merely represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A magnetic resonance scanning method, characterized in that, The method includes: Performing magnetic resonance scanning on at least one slice group of the heart of a scanned object during an initial cardiac cycle to obtain an initial cardiac localization; Based on the initial cardiac localization, obtaining an initial cardiac localization image, inputting the initial cardiac localization image into a preset deep learning network model, and obtaining a scanning orientation for the next cardiac cycle through the deep learning network model; the initial cardiac cycle and the next cardiac cycle are within a single breath-hold range of the scanned object; Scanning the at least one slice group according to the scanning orientation to obtain an orientation image of the cardiac anatomical structure.

2. The method according to claim 1, wherein Before performing magnetic resonance scanning on at least one slice group of the heart of a scanned object during the initial cardiac cycle to obtain an initial cardiac localization image, the method further includes: Adjusting the magnetic resonance scanning protocol to a multi-slice group protocol.

3. The method according to claim 1 or 2, characterized in that, The scanning orientation includes at least one of a transverse plane, a coronal plane, or a sagittal plane.

4. The method according to claim 1, wherein The method further includes: Using the orientation image of the cardiac anatomical structure to perform imaging scanning on the heart of the scanned object to obtain cardiac magnetic resonance data of the scanned object; Reconstructing the cardiac magnetic resonance data using a reconstruction algorithm to obtain a cardiac magnetic resonance image of the scanned object.

5. The method according to claim 4, wherein The reconstruction algorithm includes a Fourier transform algorithm, a compressed sensing algorithm, or a parallel reconstruction algorithm.

6. A magnetic resonance scanning device, characterized in that, The apparatus includes: A first scanning module configured to perform magnetic resonance scanning on at least one slice group of the heart of a scanned object during an initial cardiac cycle to obtain an initial cardiac localization; A determination module configured to, based on the initial cardiac localization, obtain an initial cardiac localization image, input the initial cardiac localization image into a preset deep learning network model, and obtain a scanning orientation for the next cardiac cycle through the deep learning network model; the initial cardiac cycle and the next cardiac cycle are within a single breath-hold range of the scanned object; A second scanning module configured to scan the at least one slice group according to the scanning orientation to obtain an orientation image of the cardiac anatomical structure.

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

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

Images