A magnetic resonance physics field simulation system and method

Abstract

Embodiments of the present specification provide a magnetic resonance physical field simulation system and method, the method comprising: acquiring a three-dimensional space model of a scanning room in which a nuclear magnetic resonance instrument is located; acquiring first characteristic information of the nuclear magnetic resonance instrument, the first characteristic information at least including a physical field emission model of the nuclear magnetic resonance instrument; and based on the three-dimensional space model and the first characteristic information, determining a physical field distribution of the nuclear magnetic resonance instrument in the scanning room when the nuclear magnetic resonance instrument is running by using a physical field simulation model.

Description

TECHNICAL FIELD

[0001] The present specification relates to the technical field of medical technology, and in particular to a magnetic resonance physical field simulation system and method. BACKGROUND

[0002] A nuclear magnetic resonance instrument generates high-intensity physical fields (e.g., magnetic fields, electromagnetic fields) when in operation, which can affect surrounding equipment and personnel, etc. Therefore, it is necessary to ensure that the nuclear magnetic resonance instrument and other equipment and personnel, etc. are kept at a certain distance. With the development of magnetic resonance imaging (MRI) technology, the physical field strength of the nuclear magnetic resonance instrument when in operation is becoming stronger and stronger. The distance between the nuclear magnetic resonance instrument and other equipment and personnel also needs to be increased. For example, according to the national standard, the cabinet of the MRI system must be installed at a position 10 meters away from the 3T or 5T nuclear magnetic resonance instrument. In order to meet the distance between the nuclear magnetic resonance instrument and other equipment and personnel, it is necessary to continuously expand the scanning room where the MRI system is installed. Or, in the case where the scanning room size is not enough, the scanning room needs to be coated with reflective material at different positions according to the physical field distribution in the scanning room, so as to avoid the harm of the high-intensity physical field in the scanning room to the surrounding equipment and personnel, etc.

[0003] The existing method usually performs magnetic resonance physical field simulation based on the finite element analysis (FEA) method to determine the physical field distribution in the scanning room where the nuclear magnetic resonance instrument is located. The physical field simulation based on finite element analysis mainly decomposes a 2D or 3D environment representation into a series of nodes or points, and in each calculation, the values of adjacent nodes or points need to be calculated and iterated repeatedly through a series of different algorithms. Generally, finite element analysis needs to use mesh software to decompose the model, continuously subdivide the environment and obtain nodes or points. Finite element analysis needs to manually adjust many parameters and has slow calculation speed. Therefore, the present specification hopes to provide an efficient and accurate magnetic resonance physical field simulation system and method. SUMMARY

[0004] One of the embodiments of the present specification provides a magnetic resonance physical field simulation method. The method comprises: obtaining a three-dimensional space model of a scanning room where a nuclear magnetic resonance instrument is located; obtaining first feature information of the nuclear magnetic resonance instrument, the first feature information at least including a physical field emission model of the nuclear magnetic resonance instrument; and based on the three-dimensional space model and the first feature information, determining a physical field distribution in the scanning room when the nuclear magnetic resonance instrument is in operation by using a physical field simulation model.

[0005] In some embodiments, the acquiring the three-dimensional space model of the scanning room where the nuclear magnetic resonance instrument is located comprises: acquiring point cloud data of the scanning room; and constructing at least a part of the three-dimensional space model based on the point cloud data.

[0006] In some embodiments, the determining, based on the three-dimensional space model and the first feature information, the physical field distribution in the scanning room where the nuclear magnetic resonance instrument is located when the nuclear magnetic resonance instrument is running, by using a physical field simulation model, comprises: dividing the three-dimensional space model into at least two sub-blocks; acquiring second feature information corresponding to each of the at least two sub-blocks; and determining, based on the second feature information of the at least two sub-blocks and the first feature information, the physical field distribution in the scanning room where the nuclear magnetic resonance instrument is located when the nuclear magnetic resonance instrument is running, by using a physical field simulation model.

[0007] In some embodiments, the dividing the three-dimensional space model into at least two sub-blocks comprises: acquiring reference information related to the activity range of a user in the scanning room and / or the position of the nuclear magnetic resonance instrument in the scanning room; and dividing the three-dimensional space model into at least two sub-blocks based on the reference information.

[0008] In some embodiments, the acquiring second feature information corresponding to each of the at least two sub-blocks comprises: for each of the at least two sub-blocks, acquiring third feature information of a sub-region in the scanning room corresponding to the sub-block, the third feature information comprising at least one of a physical field absorption feature and a physical field reflection feature of the sub-region; and determining the second feature information of the sub-block based on the third feature information of the sub-region.

[0009] In some embodiments, the second feature information corresponding to each sub-block comprises a feature coefficient of the sub-block, the feature coefficient being related to the size and position of the sub-block.

[0010] In some embodiments, the physical field simulation model is generated by using a model training process comprising: acquiring at least two training samples; and acquiring the physical field simulation model by training an initial model based on the at least two training samples, wherein each training sample comprises: sample first feature information related to a sample nuclear magnetic resonance instrument, sample second feature information related to a sample scanning room where the sample nuclear magnetic resonance instrument is located, and a physical field distribution in the sample scanning room where the sample nuclear magnetic resonance instrument is running.

[0011] In some embodiments, the physical field simulation model comprises a first part and a second part, wherein the first part comprises at least two first layers connected in sequence, and the number of nodes in the at least two first layers decreases in sequence; and the second part comprises at least two second layers connected in sequence, and the number of nodes in the at least two second layers increases in sequence.

[0012] In some embodiments, the method further comprises: constructing a three-dimensional virtual space of the scanning room based on the physical field distribution of the nuclear magnetic resonance instrument in the scanning room when the nuclear magnetic resonance instrument is running, the three-dimensional virtual space presenting relevant information of at least two objects in the scanning room and the physical field distribution; and displaying the three-dimensional virtual space by using a virtual reality device.

[0013] In some embodiments, the three-dimensional virtual space comprises a ground model corresponding to the ground of the scanning room, and the constructing the three-dimensional virtual space of the scanning room based on the physical field distribution of the nuclear magnetic resonance instrument in the scanning room when the nuclear magnetic resonance instrument is running comprises: dividing the scanning room into at least two regions extending in the height direction; determining a maximum physical field in each region of the at least two regions based on the physical field distribution; and generating the ground model based on the maximum physical field of each region, the ground model presenting a physical field contour map corresponding to the maximum physical field.

[0014] In some embodiments, the physical field comprises at least one of a magnetic field and an electromagnetic field.

[0015] One of the embodiments of the present specification provides a magnetic resonance physical field simulation system. The magnetic resonance physical field simulation system comprises a first acquisition module, a second acquisition module and a determination module. The first acquisition module is configured to acquire a three-dimensional space model of a scanning room where a nuclear magnetic resonance instrument is located. The second acquisition module is configured to acquire first characteristic information of the nuclear magnetic resonance instrument, the first characteristic information at least comprising a physical field emission model of the nuclear magnetic resonance instrument. The determination module is configured to determine a physical field distribution of the scanning room when the nuclear magnetic resonance instrument is running based on the three-dimensional space model and the first characteristic information by using a physical field simulation model.

[0016] Some of the additional features of the present specification can be described in the following description. Some of the additional features of the present specification are apparent to those skilled in the art based on the following description and corresponding drawings, or by practice of the methods, means and combinations set forth in the detailed examples below. The features of the present specification can be realized and obtained by practicing or using each aspect of the methods, means and combinations set forth in the detailed examples below. BRIEF DESCRIPTION OF DRAWINGS

[0017] The specification will be further described in the manner of example embodiments, which will be described in detail with reference to the accompanying drawings. The embodiments are not restrictive, and in the embodiments, the same reference numbers denote the same structures, in which:

[0018] Figure 1 is a schematic diagram of an application scenario of an example magnetic resonance physical field simulation system according to some embodiments of the present specification;

[0019] Figure 2 is a schematic diagram of an example magnetic resonance physical field simulation system according to some embodiments of the present specification;

[0020] Figure 3 is a schematic diagram of an example magnetic resonance physical field simulation method according to some embodiments of the present specification;

[0021] Figure 4 is a schematic diagram of a training process of an example physical field simulation model according to some embodiments of the present specification; and

[0022] Figure 5 is a schematic diagram of an example physical field simulation model according to some embodiments of the present specification. DETAILED DESCRIPTION

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the drawings needed to be used in the embodiment description will be briefly introduced below. Obviously, the drawings in the following description are only some examples or embodiments of the present specification, and for those skilled in the art, the present specification can be applied to other similar scenarios without creative labor. Unless it is clear from the language environment or otherwise stated, the same reference numbers in the drawings represent the same structures or operations.

[0024] It should be understood that the "system", "device", "unit" and / or "module" used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0025] As shown in the specification and claims, unless the context clearly indicates otherwise, "one", "a", "an", and / or "the" do not refer to the singular, but can also include the plural. Generally, the terms "comprise" and "include" only indicate the inclusion of the steps and elements explicitly identified, and these steps and elements do not constitute an exclusive list, and the method or device can also include other steps or elements.

[0026] Flow diagrams in the present specification are used to illustrate the operations performed by systems according to embodiments of the present specification. It should be understood that the preceding or following operations are not necessarily performed in the exact order shown. Instead, various steps can be handled in reverse order, or at the same time. Also, other operations can be added to, or removed from, these processes.

[0027] A magnetic resonance instrument emits magnetic fields (e.g., a main magnetic field generated by a main magnet) and electromagnetic fields (e.g., gradient fields generated by a gradient system) into a scan room where the magnetic resonance instrument is located when the magnetic resonance instrument is in operation. A physical field in the present specification includes at least one of a magnetic field and an electromagnetic field.

[0028] Figure 1 is a schematic diagram of an application scenario of an exemplary magnetic resonance physical field simulation system according to some embodiments of the present specification. As shown in Figure 1 The application scenario 100 of the magnetic resonance physical field simulation system can include a scan room 110, a medical device 120, a processing device 130, and a network 140. The medical device 120, the processing device 130, the network 140, and one or more other devices (e.g., an air conditioner) can be disposed in the scan room 110. In some embodiments, the processing device 130 can be disposed outside the scan room 110. In some embodiments, the processing device 130 can be part of the medical device 120. The connections between the components in the application scenario 100 can be variable. As shown in Figure 1 The medical device 120 can be connected to the processing device 130 through the network 140. For example, the medical device 120 can be directly connected to the processing device 130.

[0029] The medical device 120 can be a non-invasive scanning imaging device for disease diagnosis or research purposes. In some embodiments, the medical device 120 can scan a target object in a detection area or a scan area to obtain scan data of the target object. In some embodiments, the medical device 120 can include a magnetic resonance imaging (MRI) scanner, an X-ray imaging-magnetic resonance imaging (X-ray-MRI) scanner, a single photon emission computed tomography-magnetic resonance imaging (SPECT-MRI) scanner, a digital subtraction angiography-magnetic resonance imaging (DSA-MRI) scanner, etc. In some embodiments, the processing device 130 can be integrated on the medical device 120, or the medical device 120 and the processing device 130 can realize their functions through the same entity. The medical devices provided above are only for illustrative purposes and are not intended to limit the scope of the present specification.

[0030] The processing device 130 can process data and / or information obtained from the medical device 120, or other components (e.g., a storage device for storing data or information obtained from the medical device 120). For example, the processing device 130 can obtain a three-dimensional spatial model of the scanning room 110. The processing device 130 can also obtain first feature information of the medical device 120. The first feature information can include at least a physical field emission model of the medical device 120. Based on the obtained three-dimensional spatial model and the first feature information, the processing device 130 can determine a physical field distribution of the medical device 120 in the scanning room 110 at runtime using the physical field simulation model. In some embodiments, the processing device 130 can be local or remote. For example, the processing device 130 can access information and / or data from the medical device 120 through the network 140.

[0031] The network 140 can include any suitable network capable of facilitating the exchange of information and / or data. In some embodiments, at least one component of the application scenario 100 (e.g., the medical device 120, the processing device 130) can exchange information and / or data with at least one other component of the application scenario 100 through the network 140. For example, the processing device 130 can obtain a three-dimensional spatial model of the scanning room 110 from a storage device through the network 140. For another example, a terminal device can obtain the physical field distribution of the medical device 120 in the scanning room 110 at runtime from the processing device 130 through the network 140.

[0032] It should be noted that the application scenario 100 is provided for illustrative purposes only and is not intended to limit the scope of the present specification. Various modifications or changes can be made according to the description of the present specification by those of ordinary skill in the art. For example, the application scenario 100 can also include a storage device, a terminal device, etc. For another example, the application scenario 100 can implement similar or different functions on other devices. However, these changes and modifications will not depart from the scope of the present specification.

[0033] Figure 2 is a schematic diagram of an exemplary magnetic resonance physical field simulation system according to some embodiments of the present specification.

[0034] As shown in Figure 2 In some embodiments, the magnetic resonance physical field simulation system 200 can include a first obtaining module 210, a second obtaining module 220, a determining module 230, a model training module 240, a constructing module 250, and a displaying module 260. In some embodiments, the corresponding functions of the magnetic resonance physical field simulation system 200 can be performed by the processing device 130, for example, the first obtaining module 210, the second obtaining module 220, the determining module 230, the model training module 240, the constructing module 250, and the displaying module 260 can be modules in the processing device 130.

[0035] The first obtaining module 210 can be configured to obtain a three-dimensional space model of a scanning room in which the nuclear magnetic resonance instrument is located. In some embodiments, the first obtaining module 210 can obtain point cloud data of the scanning room, and construct the three-dimensional space model based on the point cloud data. More details about obtaining the three-dimensional space model of the scanning room in which the nuclear magnetic resonance instrument is located can be found in step 310, which will not be repeated here.

[0036] The second obtaining module 220 can be configured to obtain first characteristic information of the nuclear magnetic resonance instrument, the first characteristic information at least including a physical field emission model of the nuclear magnetic resonance instrument. More details about obtaining the first characteristic information of the nuclear magnetic resonance instrument can be found in step 320, which will not be repeated here.

[0037] The determining module 230 can be configured to determine, based on the three-dimensional space model and the first characteristic information, a physical field distribution of the nuclear magnetic resonance instrument in the scanning room when the nuclear magnetic resonance instrument is running, by using the physical field simulation model. In some embodiments, the determining module 230 can divide the three-dimensional model into at least two sub-blocks. The determining module 230 obtains second characteristic information corresponding to each of the at least two sub-blocks. The determining module 230 can also determine, based on the second characteristic information of the at least two sub-blocks and the first characteristic information, the physical field distribution of the nuclear magnetic resonance instrument in the scanning room when the nuclear magnetic resonance instrument is running, by using the physical field simulation model. More details about determining the physical field distribution of the nuclear magnetic resonance instrument in the scanning room when the nuclear magnetic resonance instrument is running can be found in step 330, which will not be repeated here.

[0038] The model training module 240 can be configured to obtain at least two training samples, and obtain the physical field simulation model by training an initial model based on the at least two training samples. Each training sample can include sample first characteristic information related to a sample nuclear magnetic resonance instrument, sample second characteristic information related to a sample scanning room in which the sample nuclear magnetic resonance instrument is located, and a physical field distribution in the sample scanning room when the sample nuclear magnetic resonance instrument is running. In some embodiments, the physical field distribution in the sample scanning room when the sample nuclear magnetic resonance instrument is running can be determined based on a finite element analysis (FEA) algorithm. More details about the training samples and training the initial model to obtain the physical field simulation model can be found in step 320, which will not be repeated here. Figure 4

[0039] The constructing module 250 can be configured to construct a three-dimensional virtual space of the scanning room based on the physical field distribution of the nuclear magnetic resonance instrument in the scanning room when the nuclear magnetic resonance instrument is running. The three-dimensional virtual space can present relevant information and the physical field distribution of one or more objects in the scanning room. More details about constructing the three-dimensional virtual space of the scanning room can be found in step 340, which will not be repeated here.

[0040] ​Display module 260 can be used to display a three-dimensional virtual space using a virtual reality device. Further details regarding the display of a three-dimensional virtual space can be found in step 350 and will not be repeated here.

[0041] It should be understood that Figure 2 The system and its modules shown can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented by hardware, software, or a combination of both.

[0042] It should be noted that the above description of the system and its modules is for illustrative purposes only and should not be construed as limiting this specification to the scope of the illustrated embodiments. It is understood that those skilled in the art, after understanding the principles of this system, may arbitrarily combine the various modules or construct subsystems connected to other modules without departing from these principles. For example, in some embodiments, Figure 2 The modules disclosed above can be different modules within a single system, or a single module can implement the functions of two or more of the modules described above. For example, modules can share a single storage module, or each module can have its own separate storage module. Such variations are all within the scope of this specification. Furthermore, in some embodiments, one or more modules in the magnetic resonance physics simulation system 200 can be implemented by other systems. That is, the aforementioned one or more modules may not be included in the magnetic resonance physics simulation system 200. For example, the model training module 240 can be a module in another system (e.g., the system of a supplier of the physics simulation model).

[0043] Figure 3 This is a flowchart illustrating an exemplary magnetic resonance physics field simulation method according to some embodiments of this specification. In some embodiments, one or more steps of process 300 may be performed... Figure 1 The application scenario 100 shown is implemented or is provided by Figure 2 The magnetic resonance physics simulation system 200 shown is executed. For example, process 300 can be executed by a module within processing device 130. Figure 3 As shown, process 300 may include the following steps.

[0044] Step 310: Obtain a three-dimensional spatial model of the scanning chamber where the MRI scanner is located. In some embodiments, step 310 may be performed by the processing device 130 or the first acquisition module 210.

[0045] An MRI scanner can be any medical device that utilizes the phenomenon of magnetic resonance, for example, Figure 1The medical device 120 is shown. The three-dimensional spatial model of the scan room refers to a three-dimensional model representing the interior scene of the scan room. In some embodiments, the three-dimensional spatial model of the scan room can be used to represent the interior spatial structure of the scan room and one or more objects located inside the scan room. The one or more objects can include objects that have been placed in the scan room and / or objects that are to be placed in the scan room. Exemplary one or more objects can include a magnetic resonance imaging machine, a cabinet, a computing device, a control device, a table and chair, a wall, a floor, etc. of the medical device system.

[0046] In some embodiments, the processing device can obtain point cloud data of the scan room. Each data point in the point cloud data can correspond to a physical point or a region of the interior scene of the scan room. The data points in the point cloud data can include information about their corresponding physical points (or physical regions), such as the location of the physical point, the object to which the physical point belongs, etc. In some embodiments, the point cloud data can be obtained by a sensor (e.g., a LiDAR). For example, the sensor can emit laser pulses to scan the interior space of the scan room. The laser pulses can be reflected by physical points in the interior space of the scan room and returned to the sensor. The sensor can generate point cloud data representing the scan room based on one or more characteristics of the returned laser pulses. In some embodiments, the point cloud data can be collected during a time period when the magnetic resonance imaging machine stops scanning. During the collection of the point cloud data, the sensor can rotate within a scan angle range (e.g., 360 degrees, 180 degrees, 120 degrees) and scan the interior space of the scan room at a certain scan frequency (e.g., 10 Hz, 15 Hz, 20 Hz). The processing device can construct at least a portion of the three-dimensional spatial model of the scan room based on the point cloud data. For example, the processing device can construct an initial three-dimensional model of the interior space of the scan room and the one or more objects located inside the scan room based on the coordinate system and scale of the three-dimensional spatial model and the information contained in the point cloud data.

[0047] In some embodiments, the initial three-dimensional spatial model of the scan room can be generated based on a plurality of two-dimensional images. In some embodiments, the plurality of two-dimensional images can be images taken in advance. The processing device can reconstruct the three-dimensional spatial model from the plurality of two-dimensional images taken in advance by a three-dimensional reconstruction technique. Exemplary three-dimensional reconstruction techniques can include a shape from texture (SFT) method, a shape from shading method, a multi-view stereo (MVS) method, a structure from motion (SFM) method, a time-of-flight (ToF) method, a structured light method, a moire shadow method, etc., or any combination thereof.

[0048] In some embodiments, the processing device can also obtain the initial three-dimensional space model in other ways. For example, the processing device can use a depth camera to collect depth data of the scanned indoor scene, and then obtain the initial three-dimensional space model according to the depth data. For another example, the processing device can obtain the three-dimensional space model by manual drawing, surveying, or the like, and the present specification does not limit the method of obtaining the three-dimensional space model.

[0049] The processing device can further construct a three-dimensional model corresponding to one or more objects to be placed in the scanning room in the initial three-dimensional model based on related information (e.g., size, planned placement position, etc.) of the one or more objects to be placed in the scanning room, to obtain the three-dimensional space model of the scanning room.

[0050] In some embodiments, the three-dimensional space model can also be generated in advance and stored in a storage device or a database. The processing device 130 can obtain the three-dimensional space model of the scanning room from the storage device or the database.

[0051] In step 320, first characteristic information of the nuclear magnetic resonance instrument is obtained, and the first characteristic information at least includes a physical field emission model of the nuclear magnetic resonance instrument. In some embodiments, step 320 can be performed by the processing device 130 or the second obtaining module 220.

[0052] The physical field emission model can represent the physical field emission characteristics of the nuclear magnetic resonance instrument when the nuclear magnetic resonance instrument is running. For example, the physical field emission model can include the intensity of the physical field emitted by the nuclear magnetic resonance instrument to different positions when the nuclear magnetic resonance instrument is running. In some embodiments, since the intensity of the physical field emitted by the nuclear magnetic resonance instrument when the nuclear magnetic resonance instrument is running changes, the processing device can determine the physical field emission model according to the maximum intensity of the physical field emitted by the nuclear magnetic resonance instrument when the nuclear magnetic resonance instrument is running. In some embodiments, the processing device can determine the physical field emission model according to one or more performance parameters of components of the nuclear magnetic resonance instrument for emitting a magnetic field and / or an electromagnetic field. For example, the processing device can obtain the magnetic field intensity emitted by the main magnet to different positions when the nuclear magnetic resonance instrument is running. For each position in the scanning room, the processing device can take the magnetic field intensity at the position as the physical field intensity of the position, and thus can determine the physical field emission model. For another example, the processing device can obtain the magnetic field intensity emitted by the main magnet to different positions when the nuclear magnetic resonance instrument is running and the maximum electromagnetic field intensity (i.e., the maximum gradient field intensity) that can be emitted by the gradient system to different positions. For each position in the scanning room, the processing device can take the sum of the magnetic field intensity at the position and the maximum electromagnetic field intensity as the physical field intensity of the position, and thus can determine the physical field emission model.

[0053] In some embodiments, the first physical field intensity contour map can be used to represent the physical field emission model. In the first physical field intensity contour map, the position points with equal or similar physical field intensity emitted by the MRI are connected to form closed curves, and the corresponding physical field intensity is marked on different closed curves. In some embodiments, the first physical field intensity contour map can be a three-dimensional contour map or a two-dimensional contour map.

[0054] In some embodiments, the first characteristic information can further include other information related to the MRI, such as the position (or the position to be placed) of the MRI, the size, the weight, and the like. In some embodiments, the processing device can obtain the first characteristic information from one or more components in the application scenario 100 of the magnetic resonance physical field simulation system or an external device.

[0055] At step 330, based on the three-dimensional space model and the first characteristic information, the physical field distribution of the MRI in the scanning room during operation is determined by using the physical field simulation model. In some embodiments, step 330 can be performed by the processing device 130 or the determination module 230.

[0056] The physical field distribution refers to the distribution rule of the physical field intensity of the MRI at different positions in the scanning room during operation. The MRI will radiate physical fields in all directions during operation, and these physical fields can be reflected or absorbed by other devices in the scanning room, forming the final physical field distribution. In some embodiments, the physical field distribution can be represented by a three-dimensional model with physical field intensity information. In some embodiments, similar to the physical field emission model described in step 320, a second physical field intensity contour map can be used to represent the physical field distribution of the MRI in the scanning room during operation. In the second physical field intensity contour map, the position points with equal or similar physical field intensity in the scanning room are connected to form closed curves, and the corresponding physical field intensity is marked on different closed curves. In some embodiments, the second physical field intensity contour map can be a three-dimensional contour map or a two-dimensional contour map.

[0057] In some embodiments, the processing device can divide the three-dimensional space model into at least two sub-blocks. Each sub-block can correspond to a physical region in the scanning room and an object existing in the region. In some embodiments, the processing device can divide the three-dimensional space model into at least two sub-blocks with the same size according to a preset sub-block size. For example, the processing device can divide the three-dimensional space model into at least two sub-blocks with different sizes according to a plurality of different preset sub-block sizes and a region corresponding to each preset sub-block size.

[0058] In some embodiments, the processing device can obtain reference information, and divide the three-dimensional model into at least two sub-blocks based on the reference information. In some embodiments, the reference information is related to the range of the user's activities in the scanning room. For example, the processing device can determine a target region in the three-dimensional model corresponding to the range of the user's activities in the scanning room according to the correspondence between the three-dimensional model and the internal space of the scanning room. Alternatively, the user can manually determine the target region in the three-dimensional model corresponding to the range of the user's activities in the scanning room. For example, the user can draw the target region in the three-dimensional model directly in the three-dimensional model through the display device. Alternatively, the processing device can determine the target region corresponding to the range of activities according to the historical activity trajectory of the user in the scanning room. Further, the processing device can divide the three-dimensional model based on the target region. In which, the size of the sub-block in the target region is smaller than that of the sub-block in other regions.

[0059] In some embodiments, the reference information is related to the position of the nuclear magnetic resonance instrument in the scanning room, and the processing device can divide the three-dimensional model based on the position of the nuclear magnetic resonance instrument. In which, the closer to the nuclear magnetic resonance instrument, the smaller the size of the sub-block in the region. In some embodiments, the reference information can be related to the position of one or more important devices in the scanning room. The one or more important devices can include devices that are easily affected by physical fields (for example, devices whose probability of being damaged under the strong physical field emitted by the nuclear magnetic resonance instrument is greater than a certain threshold). The processing device can divide the three-dimensional model based on the position of the one or more important devices. In which, the closer to the one or more important devices, the smaller the size of the sub-block in the region. In some embodiments, the processing device can divide the three-dimensional model based on multiple reference information.

[0060] Based on the reference information, the key regions in the three-dimensional model (for example, the target region corresponding to the range of the user's activities, the region close to the nuclear magnetic resonance instrument, and the region close to the one or more important devices) can be densely divided into sub-blocks, and other regions (for example, the high-altitude region of the scanning room away from the nuclear magnetic resonance instrument) can be divided into fewer sub-blocks. In this way, under the condition that the accuracy of the obtained data meets the requirements, the number of sub-blocks in other regions can be reduced, thereby reducing the amount of subsequent data processing (for example, the amount of data input into the model can be greatly reduced), thereby improving the efficiency of physical field simulation and saving computing resources.

[0061] Further, the processing device can obtain second characteristic information corresponding to each of the at least two sub-blocks, and determine the physical field distribution in the scanning chamber when the nuclear magnetic resonance instrument is running based on the first characteristic information of the nuclear magnetic resonance instrument and the second characteristic information of each of the sub-blocks. In some embodiments, the processing device can determine the correspondence between the at least two sub-blocks and the sub-regions in the scanning chamber according to the correspondence between the three-dimensional space model and the scanning chamber. For each of the sub-blocks, the processing device can determine the second characteristic information of the sub-block based on the sub-region corresponding to the sub-block. The second characteristic information corresponding to each of the sub-blocks can include the position of the sub-block (or the position of the sub-region corresponding to the sub-block), the size of the sub-block (or the size of the sub-region corresponding to the sub-block), the physical field characteristic of the sub-region corresponding to the sub-block, and the like. In some embodiments, for each of the at least two sub-blocks, the processing device can obtain third characteristic information of the sub-region in the scanning chamber corresponding to the sub-block. In some embodiments, the third characteristic information of each of the sub-regions at least includes at least one of the physical field absorption characteristic and the physical field reflection characteristic of the sub-region, for example, the physical field absorption rate and the physical field reflection rate. For each of the at least two sub-blocks, the processing device can determine the second characteristic information of the sub-block based on the third characteristic information of the corresponding sub-region. For example, the third characteristic information of each of the sub-regions includes the physical field absorption rate and the physical field reflection rate of the sub-region, and the processing device can determine a first characteristic coefficient with a value in the range of -1 to 1 as the second characteristic information of the sub-block corresponding to the sub-region based on the physical field absorption rate and the physical field reflection rate of each of the sub-regions. For example only, if one of the sub-regions is a vacuum region, the first characteristic coefficient (i.e., the second characteristic information) of the sub-block corresponding to the sub-region is 0. If one of the sub-regions can reflect 100% of the physical field, the first characteristic coefficient (i.e., the second characteristic information) of the sub-block corresponding to the sub-region is 1; if one of the sub-regions can absorb 100% of the physical field, the first characteristic coefficient (i.e., the second characteristic information) of the sub-block corresponding to the sub-region is -1.

[0062] In some embodiments, the second characteristic information of each of the sub-blocks can include a second characteristic coefficient corresponding to the sub-block. The second characteristic coefficient can be related to the size and position of the sub-block. In some embodiments, the processing device can determine the second characteristic coefficient of the sub-block based on the size and position of the sub-block. For example, the processing device can determine a reference point (for example, a point on the nuclear magnetic resonance instrument), and determine the distance from the reference point to the position of each of the sub-blocks. The processing device can determine the second characteristic coefficient corresponding to each of the sub-blocks according to the relationship between the second characteristic coefficient of the sub-block and the size of the sub-block and the distance from the reference point.

[0063] In some embodiments, the processing device can determine the physical field distribution in the scanning chamber when the nuclear magnetic resonance instrument is running based on the second characteristic information of the at least two sub-blocks and the first characteristic information by using a physical field simulation model.

[0064] A physics simulation model can be a model used to determine the distribution of physical fields. In some embodiments, the physics simulation model may include an input layer, a first part, a second part, and an output layer connected in sequence. In some embodiments, the first part may include at least two first layers connected in sequence, with the number of nodes in the at least two first layers decreasing sequentially. The second part may include at least two second layers connected in sequence, with the number of nodes in the at least two second layers increasing sequentially. That is, the model size gradually decreases in the first part of the physics simulation model and gradually increases in the second part. In some embodiments, the first layer with the most nodes in the first part may be connected to the input layer, and the first layer with the fewest nodes may be connected to the second part. In some embodiments, the second layer with the fewest nodes in the second part may be connected to the first part, and the second layer with the most nodes in the second part may be connected to the output layer. In some embodiments, the first layer with the most nodes in the first part may be connected to the input layer, the first layer with the fewest nodes may be connected to the second layer with the fewest nodes in the second part, and the second layer with the most nodes in the second part may be connected to the output layer. Using this model structure, the data in the input model can be processed with relatively fewer nodes, thereby reducing the computational load of the model and improving the efficiency of model computation.

[0065] Just as an example, Figure 5 This is a schematic diagram of an exemplary physics simulation model 500 according to some embodiments of this specification. For example... Figure 5 As shown, the physics simulation model 500 may include an input layer 502, a first part 504, a second part 506, and an output layer 508. The first part 504 may include three sequentially connected first layers 504-1, 504-2, and 504-3. The second part 506 may include three sequentially connected second layers 506-1, 506-2, and 506-3. As can be seen from the figure, the first layer 504-1 includes 4 nodes (i.e., Figure 5 The first layer (504-2) has 3 nodes, and the first layer (504-3) has 2 nodes. That is, the number of nodes in the three first layers (504-1, 504-2, and 504-3) decreases sequentially. The second layer (506-1) has 3 nodes, the second layer (506-2) has 4 nodes, and the second layer (506-3) has 5 nodes. That is, the number of nodes in the three second layers (506-1, 506-2, and 506-3) increases sequentially. The first layer (504-1) with the most nodes is connected to the input layer, the first layer (504-3) with the fewest nodes is connected to the second layer (506-1) with the fewest nodes, and the second layer (506-3) with the most nodes is connected to the output layer.

[0066] In some embodiments, the physical field simulation model can include a Convolutional Neural Network (CNN), a Residual Network (ResNet), or the like. In some embodiments, the processing device can obtain the physical field simulation model from Figure 1 The one or more components or external devices of the application scenario 100 of the magnetic resonance physical field simulation system obtain the physical field simulation model. For example, the physical field simulation model can be trained by a computing device (e.g., the processing device 130) and stored in a storage device of the application scenario 100. The processing device can access the storage device and retrieve the physical field simulation model. In some embodiments, the physical field simulation model can be obtained by training an initial model based on a plurality of training samples. For more information about model training, see Figure 4 and the related description, which is not repeated here.

[0067] In some embodiments, the processing device can input the second feature information and the first feature information of the at least two sub-blocks into the physical field simulation model, and the physical field simulation model can output the physical field distribution of the scan chamber when the magnetic resonance instrument is running. For example, as described above, the second feature information can include the position, size, and first feature coefficient of each sub-block. The processing device can input the first feature information and the position, size, and first feature coefficient of each sub-block into the physical field simulation model. For another example, the second feature information can include the first feature coefficient and the second feature coefficient of each sub-block. The processing device can input the first feature information and the first feature coefficient and the second feature coefficient of each sub-block into the physical field simulation model. Using the second feature coefficient to represent the position and size of each sub-block can reduce the amount of data input into the model, thereby reducing the amount of data processing of the model to improve the efficiency of the system. In some embodiments, the first feature information and the second feature information can be converted into numerical arrays before being input into the physical field simulation model. In some embodiments, the second feature information of each sub-block can be input into the physical field simulation model separately. Alternatively, the at least two sub-blocks can be divided into at least two batches, and the second feature information of the sub-blocks in the same batch can be input into the physical field simulation model each time. Alternatively, the second feature information of all sub-blocks can be input into the physical field simulation model all at once. In some embodiments, the physical field simulation model can directly output the physical field distribution of the scan chamber when the magnetic resonance instrument is running. In some embodiments, the physical field simulation model can output information related to the physical field distribution. For example, the physical field simulation model can output the physical field strength corresponding to each sub-block. The processing device can determine the physical field distribution based on the physical field strength corresponding to each sub-block.

[0068] In some embodiments, the processing device can determine, according to the physical field distribution in the scanning chamber when the magnetic resonance imaging device is in operation and the maximum physical field intensity that each object located in the scanning chamber can withstand, the relevant information of the shielding layer needed to be used in different regions in the scanning chamber. The exemplary relevant information of the shielding layer can include the material, thickness, size of the shielding region, etc. of the shielding layer.

[0069] In some embodiments, the processing device can determine, according to the physical field distribution in the scanning chamber when the magnetic resonance imaging device is in operation and the maximum physical field intensity that one or more objects located in the scanning chamber can withstand, whether the position of the one or more objects in the scanning chamber needs to be adjusted. For example, when it is determined, according to the physical field distribution in the scanning chamber when the magnetic resonance imaging device is in operation, that the physical field intensity of the magnetic resonance imaging device in operation at the position corresponding to a target object exceeds a certain threshold value (e.g., the maximum physical field intensity that the target object can withstand), it can be determined that the position of the target object in the scanning chamber needs to be adjusted. In some embodiments, after adjusting the position of one or more objects in the scanning chamber, steps 310-330 can be repeated to re-determine the physical field distribution in the scanning chamber when the magnetic resonance imaging device is in operation. In some embodiments, after adjusting the position of one or more objects in the scanning chamber, the physical field distribution in the scanning chamber when the magnetic resonance imaging device is in operation can be re-determined for all regions in the entire scanning chamber. In some embodiments, after adjusting the position of one or more objects in the scanning chamber, the physical field distribution in the scanning chamber when the magnetic resonance imaging device is in operation can be re-determined for at least two regions in the scanning chamber that have changed.

[0070] Step 340, constructing a three-dimensional virtual space of the scanning chamber based on the physical field distribution in the scanning chamber when the magnetic resonance imaging device is in operation. In some embodiments, step 340 can be performed by the processing device 130 or the construction module 250.

[0071] The three-dimensional virtual space of the scan room can be a virtual architectural space that displays the interior scene of the scan room and the physical field distribution of the interior space of the scan room. The three-dimensional virtual space can present the relevant information of one or more objects (e.g., a nuclear magnetic resonance instrument, a cabinet machine, a table and chair, etc.) in the scan room and the physical field distribution described in step 310. In some implementations, the physical field distribution can be represented using a three-dimensional model with physical field intensity information. As described in step 310, the three-dimensional space model of the scan room can represent the interior space structure of the scan room and one or more objects (e.g., a nuclear magnetic resonance instrument, a cabinet machine, a table and chair, etc.) located in the interior of the scan room. The processing device can construct a three-dimensional virtual space of the scan room based on the physical field distribution of the nuclear magnetic resonance instrument in the scan room when in operation and the three-dimensional space model of the scan room. For example, the processing device can use virtual reality technology to extend the three-dimensional space model of the scan room based on the physical field distribution of the nuclear magnetic resonance instrument in the scan room when in operation and the three-dimensional space model of the scan room, give the interior space of the scan room and one or more objects located in the scan room material and texture characteristics, and generate a three-dimensional virtual view of the architectural space of the scan room. The processing device can perform three-dimensional rendering processing on the three-dimensional virtual view of the architectural space of the scan room to present a lively three-dimensional virtual effect drawing of the architectural space. Merely as an example, the processing device can render the corresponding regions in the three-dimensional virtual space using the same colors as the regions in the scan room, so that the constructed three-dimensional virtual space is as close to the scan room as possible. Further, the processing device can also superimpose physical field distribution information (e.g., physical field intensity contour map) in the rendered three-dimensional virtual effect drawing according to the obtained physical field distribution, for example, different physical field intensities can be presented using different colors or digital labels.

[0072] In some embodiments, the three-dimensional virtual space can display the maximum physical field distribution of the scanning room in the height direction (i.e., the direction from the floor to the top of the scanning room). In some embodiments, the processing device can divide the scanning room into a plurality of regions extending along the height direction. Based on the obtained physical field distribution, the processing device can determine the maximum physical field in each region, i.e., the maximum physical field in the direction from the floor to the top. The three-dimensional virtual space corresponding to the scanning room can include a floor model corresponding to the floor of the scanning room. The processing device can generate the floor model based on the maximum physical field of each region. For example only, the physical field strength of each position on the floor can be determined first, where the physical field strength of each position is equal to the maximum physical field of the region in which the position is located. That is, the physical field of each position on the floor is equal to the maximum physical field in the direction from the floor to the top. Further, the physical field contour map can be displayed in the floor model based on the physical field strength of each position on the floor. Since the device is usually placed on the floor, displaying the physical field contour map corresponding to the maximum physical field in the height direction on the floor can help the user quickly determine the maximum physical field distribution in the height direction, which is beneficial for the user to quickly decide the placement area of the object. At the same time, displaying the maximum physical field on the floor instead of in the three-dimensional space can make the generated three-dimensional virtual space more concise and intuitive.

[0073] In some embodiments, the processing device can divide the scanning room into layers along the target direction (e.g., the height direction from the floor to the top of the scanning room, the horizontal direction perpendicular to the height direction, the direction extending along a certain wall surface). Further, in the three-dimensional virtual space generated based on the physical field distribution, the physical field contour of each layer can be included. The user can select to display the physical field contour map of a certain layer as needed, so as to facilitate the user to quickly determine the physical field distribution of different regions, which is beneficial for the user to quickly and accurately decide the placement area of the object, etc.

[0074] Step 350, displaying the three-dimensional virtual space by using the virtual reality device. In some embodiments, step 350 can be performed by the processing device 130 or the display module 260.

[0075] The exemplary virtual reality device can include an AR device, a VR device, etc. In some embodiments, the user can view the three-dimensional virtual space through the virtual reality device. For example, the user can wear VR glasses to view the position of one or more objects in the three-dimensional virtual space. For another example, the user can view the distribution of the physical field in the scanning room through the virtual reality device.

[0076] In some embodiments, a user enters the scan room when the MRI is running, and can feel the intensity of the physical field at different locations in the scan room through some wearable devices (e.g., smart clothes). In some embodiments, a user enters the scan room when the MRI is running (e.g., when the MRI is being maintained), and the virtual reality device (e.g., an AR device) can display the physical field information of the area where the user is located according to preset rules. For example, the preset rules indicate that different physical field intensity ranges correspond to different colors, and when the user enters different areas in the scan room, the virtual reality device can display the three-dimensional virtual space as the corresponding color according to the real-time location of the user and the distribution of the physical field. For example, if the user enters an area with a strong physical field, the virtual reality device can display the three-dimensional space as red, i.e., all the objects the user sees are red, to warn the user of entering a strong physical field area. In some embodiments, when the user enters a strong physical field area, the virtual reality device can directly sound an alarm to remind the user. In some embodiments, the virtual reality device can send a prompt to a monitoring personnel or a monitoring device to prompt the corresponding device or personnel to handle in a timely manner. The virtual reality device displays the physical field information of the area where the user is located to the user to timely remind the user whether to enter a strong physical field area, thereby ensuring the safety of the user.

[0077] In some embodiments, a user can simulate the physical field situation when the user enters different locations in the scan room when the MRI is running through the three-dimensional virtual space of the scan room. For example, the user can control the virtual user to move in the three-dimensional virtual space through a virtual reality device (e.g., a VR device), and the virtual reality device can display the physical field information of the area where the virtual user is located according to preset rules. For example, the preset rules indicate that different physical field intensity ranges correspond to different colors, and when the virtual user enters different areas in the virtual scan room, the virtual reality device can display the three-dimensional virtual space as the corresponding color according to the real-time location of the virtual user and the distribution of the physical field. For example, if the virtual user enters an area with a strong physical field, the virtual reality device can display the three-dimensional space as red to warn the virtual user of entering a strong physical field area. In some embodiments, when the virtual user enters a strong physical field area, the virtual reality device can directly sound an alarm to remind the user. In this way, the user can have an intuitive visual presentation of the intensity distribution of the physical field at different locations in the scan room when the MRI is running, thereby avoiding the danger that the user may cause in the real world when the user enters the scan room when the MRI is running, and ensuring the safety of the user.

[0078] It should be noted that the above description of the flow 300 is merely for example and illustration, and does not limit the scope of the present specification. Various modifications and changes can be made to the flow 300 under the guidance of the present specification by those skilled in the art. However, these modifications and changes are still within the scope of the present specification. For example, a Computed Tomography (CT) device, an X-ray scanning device, or other medical devices that can emit radiation rays that are harmful to the human body or electronic devices can also determine the radiation intensity distribution in the scanning room when the medical device is running by using the principles similar to those of the present specification.

[0079] Figure 4 is a flowchart of a training process of an exemplary physical field simulation model according to some embodiments of the present specification. In some embodiments, the flow 400 can be performed by the application scenario 100 (such as the processing device 130) or the magnetic resonance physical field simulation system 200, for example, by the corresponding modules in the processing device 130. As shown in the flow 400, the flow 400 can include the following steps. Figure 4

[0080] Step 410, obtaining at least two training samples. In some embodiments, the step 410 can be performed by the processing device 130 or the model training module 240.

[0081] In some embodiments, each training sample can include sample first feature information related to a sample nuclear magnetic resonance instrument, sample second feature information related to a sample scanning room where the sample nuclear magnetic resonance instrument is located, and a physical field distribution in the sample scanning room when the sample nuclear magnetic resonance instrument is running.

[0082] The sample first feature information at least includes a physical field emission model of the sample nuclear magnetic resonance instrument. In some embodiments, the sample first feature information can also include other information related to the sample nuclear magnetic resonance instrument, for example, the position of the sample nuclear magnetic resonance instrument. In some embodiments, the manner of obtaining the first feature information and the manner of obtaining the sample first feature information can be similar, and the related description can be referred to the step 320, which will not be repeated here.

[0083] ​The sample second feature information related to the sample scanning chamber refers to sample second feature information of a sample three-dimensional space model of the sample scanning chamber. In some embodiments, the processing device can obtain the sample three-dimensional space model in a manner similar to obtaining the three-dimensional space model of the scanning chamber, and the related description can be referred to step 310, which will not be repeated here. In some embodiments, the processing device can divide the sample three-dimensional space model into a plurality of sample sub-blocks. Each sample sub-block can correspond to a sample physical region in the sample scanning chamber and a sample object present in the sample region. The sample second feature information can include sample second feature information corresponding to each sample sub-block. In some embodiments, the sample second feature information corresponding to each sample sub-block can include the position of the sample sub-block (or the position of the sample sub-region corresponding to the sample sub-block), the size of the sample sub-block (or the size of the sample sub-region corresponding to the sample sub-block), and the physical field characteristics of the sample sub-region corresponding to the sample sub-block. In some embodiments, the processing device can determine the sample first feature coefficient corresponding to each sample sub-block based on the physical field characteristics of the sample sub-region corresponding to the sample sub-block. In some embodiments, the sample second feature information of each sample sub-block can include the sample second feature coefficient corresponding to the sample sub-block. The sample second feature coefficient can be related to the size and position of the sample sub-block. In some embodiments, the processing device can obtain a plurality of sample sub-blocks and sample second feature information of each sample sub-block in a manner similar to obtaining at least two sub-blocks and obtaining second feature information of each sub-block, and the related description can be referred to step 330, which will not be repeated here.

[0084] In some embodiments, the distribution of the physical field in the sample scanning chamber during the operation of the sample nuclear magnetic resonance instrument can be artificially calibrated or confirmed as the training true value. In some embodiments, the distribution of the physical field in the sample scanning chamber during the operation of the sample nuclear magnetic resonance instrument can be determined by the processing device based on an existing physical field simulation algorithm. In some embodiments, the distribution of the physical field in the sample scanning chamber during the operation of the sample nuclear magnetic resonance instrument can be determined based on a finite element analysis (FEA) algorithm.

[0085] Step 420, obtaining a physical field simulation model by training an initial model based on at least two training samples. In some embodiments, step 420 can be performed by processing device 130 or model training module 240.

[0086] In some embodiments, the structure and type of the initial model can be the same as the type of the physical field simulation model, and the related description can be referred to step 330, which will not be repeated here. In some embodiments, the processing device can obtain the initial model from one or more components of the application scenario 100 or external devices through a network (for example, network 140).

[0087] The training of the initial model can include one or more iterations, and in each iteration, the model parameters of the initial model can be updated based on the training samples. In some embodiments, the optimization objective of the initial model training can include adjusting the model parameters so that the value of the loss function becomes smaller (e.g., minimizing the value of the loss function). The loss function can be used to characterize the difference between the physical field distribution predicted by the initial model and the true value of the physical field distribution in the sample scanning chamber when the sample nuclear magnetic resonance instrument is running. For example, the loss function can include a focal loss function, a logarithmic loss function, a cross-entropy loss, etc. For example, the position and size of each sample patch, the sample first coefficient corresponding to each sample patch, and the sample first feature information in each training sample can be input into the initial model. For another example, the processing device can input the sample first feature coefficient and the sample second feature coefficient corresponding to each sample patch, and the sample first feature information into the initial model. The initial model can output the physical field distribution of the training sample. The loss function can be used to characterize the difference between the predicted value of the physical field distribution of the training sample and the true value of the physical field distribution in the sample scanning chamber when the sample nuclear magnetic resonance instrument is running.

[0088] In some embodiments, the initial model satisfies the termination condition in a certain iteration, the training can be stopped. For example, the termination condition can include any one or a combination of the following: the value of the loss function obtained in a certain iteration is less than a threshold value, a certain number of iterations have been performed, the loss function converges (e.g., the difference between the value of the loss function obtained in the previous iteration and the value of the loss function obtained in the current iteration is within a preset threshold), etc. In some embodiments, when the iteration does not satisfy the termination condition, the processing device can further update the initial model according to a preset algorithm (e.g., a back propagation algorithm) for the next iteration. If the termination condition is satisfied in the current iteration, the processing device can complete the training of the initial model.

[0089] According to some embodiments of the present specification, the training of the physical field simulation model using the machine learning algorithm can learn the optimal mechanism of the physical field simulation from the big data, and mine the relationship between various dimensions of data (e.g., the position information of each region in the scanning chamber, the physical field feature information, and the feature information of the nuclear magnetic resonance instrument). Such relationship often includes deep relationships that are difficult to obtain by traditional physical field simulation methods or artificial determination of physical field distribution methods. Therefore, using the physical field simulation model can improve the accuracy of the obtained physical field distribution.

[0090] In some embodiments of the present specification, the physical field distribution of the scanning room of the nuclear magnetic resonance instrument in operation is determined by a magnetic resonance physical field simulation system and method. The beneficial effects brought by the embodiments of the present specification may include but are not limited to: (1) the physical field distribution of the scanning room of the nuclear magnetic resonance instrument in operation can be determined by using the physical field simulation model, which can reduce the workload and manual intervention of the user, thereby improving the accuracy and efficiency of determining the physical field distribution in the scanning room; (2) when the three-dimensional space model is divided, some key areas in the three-dimensional space model can be densely divided, and fewer blocks can be divided for other areas. In this way, under the condition that the accuracy of the obtained data meets the requirements, the number of blocks in other areas can be reduced, thereby reducing the subsequent data processing amount (for example, the amount of data input into the model can be greatly reduced), thereby improving the efficiency of the physical field simulation and saving computing resources; (3) the second characteristic coefficient corresponding to each block can be determined, and the second characteristic coefficient corresponding to each block is used to replace the position and size parameters of each block as the input of the physical field simulation model, thereby reducing the data processing amount of the model by reducing the data input amount of the model, to improve the efficiency of the system; (4) the structure of the physical field simulation model is optimized, the data in the input model is processed by relatively fewer nodes, thereby reducing the calculation amount of the model and improving the efficiency of the model calculation; (5) displaying the maximum physical field distribution of the scanning room in the height direction on the ground can help the user quickly determine the maximum physical field distribution in the height direction, which is beneficial to the user to quickly determine the placement area of the object. At the same time, displaying the maximum physical field on the ground instead of displaying the maximum physical field in the three-dimensional space can make the generated three-dimensional virtual space more concise and intuitive; (6) in the three-dimensional virtual space generated based on the physical field distribution, the physical field contour line corresponding to each layer can be included. The user can select to display the physical field contour line of a certain layer according to the needs, so as to quickly determine the physical field distribution of different areas, which is beneficial to the user to quickly and accurately determine the placement area of the object, etc.; (7) the virtual reality device displays the physical field information of the area where the user is located to the user in time to remind the user whether to enter the strong physical field area, thereby ensuring the safety of the user; (8) the user can simulate the physical field situation of the user entering different positions in the scanning room when the nuclear magnetic resonance instrument is in operation through the three-dimensional virtual space of the scanning room. In this way, the user can have an intuitive visual presentation of the physical field intensity distribution at different positions in the scanning room when the nuclear magnetic resonance instrument is in operation, thereby avoiding the danger that the user may cause in the real world when the nuclear magnetic resonance instrument is in operation, and ensuring the safety of the user.

[0091] Having described the basic concepts, it is obvious to those skilled in the art that the foregoing detailed disclosure is intended to be illustrative only and not limiting of the scope of the present description. Although specific modifications, improvements, and alterations to the present description have not been described above, it is of course contemplated that they will not depart from the spirit and scope of the exemplary embodiments of the present description.

[0092] Also, the present description can use particular terminology when describing certain elements of the present description. For example, the phrases "one embodiment," "an embodiment," and / or "some embodiments" can each refer to some feature, structure or characteristic in relation to a one or more embodiments of the present description. As such, the use of such phrases in various places of the present description are not necessarily referring to the same embodiment(s). Further, where the description indicates there are "a" or "an" of a feature, structure or characteristic, this is also to be construed to cover both instances where one of something is present and instances where plural of that something are present.

[0093] Further, the order in which the processor elements are listed in the above-disclosed description and the order in which the processor elements are listed in the claims do not necessarily correspond, no such order should be inferred, unless the explicit claim itself directs otherwise. Additionally, use of ordinal terms such as "first," "second," "third," etc., in the claims to describe various claim elements will typically be understood and interpreted to also allow for there to be one or more elements of a claim prior to those elements. Further, the use of terms such as "about" and "substantially" are used to allow for a claim to anticipate variations from the exact numerical values specifying the limit of a given element so long as those variations do not materially alter the average technician's understanding of one or more aspects of the application. As such, specific numerical data should not be taken literally as definitions of the present description, but the skilled artisan will appreciate the reasons for the use of such data. Additionally, the use of the term "means" in the claims is intended to invoke 35 U.S.C. § 112, paragraph 6, and allow for equivalence in structure, functionality, or both, of the claimed means plus function claims.

[0094] Similarly, it is to be noticed that the term "comprising", used in the description, should not be interpreted as being restricted only to the elements or steps listed thereafter; it does not exclude other elements or steps. It is thus to be understood that, similarly, the terms "comprising" also "consisting of should not be interpreted as being restricted to the elements or steps listed thereafter when used in the description. Furthermore, the words "a" or "an" shall not be construed as "one", unless expressly so defined. The words "by the" inserted between "comprising" and "a" or "of" should not be interpreted as limiting the scope of the present description.

[0095] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters should take into account specified significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of range in some embodiments of this specification are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0096] For each patent, patent application, patent application publication, and other material, such as articles, books, specifications, publications, and documents, referenced in this specification, the entire contents of which are incorporated herein by reference. This excludes historical application documents that are inconsistent with or conflict with the content of this specification, as well as documents that limit the broadest scope of the claims in this specification (currently or subsequently appended to this specification). It should be noted that in the event of any inconsistency or conflict between the descriptions, definitions, and / or terminology used in the supplementary materials to this specification and the content of this specification, the descriptions, definitions, and / or terminology used in this specification shall prevail.

[0097] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A magnetic resonance physics field simulation method, executed by at least one processor, characterized in that, The method comprises: acquiring a three-dimensional space model of a scanning room where a nuclear magnetic resonance instrument is located; acquiring first characteristic information of the nuclear magnetic resonance instrument, the first characteristic information at least including a physical field emission model of the nuclear magnetic resonance instrument; acquiring reference information; based on the reference information, dividing the three-dimensional space model into at least two blocks of different sizes, the reference information including a range of activities of a user in the scanning room and / or a position of a device whose probability of being damaged under a physical field emitted by the nuclear magnetic resonance instrument is greater than a threshold value; acquiring second characteristic information corresponding to each block of the at least two blocks, the second characteristic information including first characteristic coefficients and second characteristic coefficients, the first characteristic coefficients being related to physical field absorption characteristics and physical field reflection characteristics of a sub-region in the scanning room corresponding to the block, and the second characteristic coefficients being related to a position and a size of the block; and based on the second characteristic information and the first characteristic information of the at least two blocks, determining a physical field distribution in the scanning room when the nuclear magnetic resonance instrument is running by using a physical field simulation model.

2. The method of claim 1, wherein, The acquisition of the three-dimensional space model of the scanning room where the nuclear magnetic resonance instrument is located comprises: acquiring point cloud data of the scanning room; and based on the point cloud data, constructing at least a part of the three-dimensional space model.

3. The method of claim 1, wherein, The physical field simulation model is generated by using a model training process as follows: acquiring at least two training samples; and based on the at least two training samples, acquiring the physical field simulation model by training an initial model, wherein each training sample includes: sample first characteristic information related to a sample nuclear magnetic resonance instrument, sample second characteristic information related to a sample scanning room where the sample nuclear magnetic resonance instrument is located, and a physical field distribution in the sample scanning room when the sample nuclear magnetic resonance instrument is running. The sample three-dimensional space model is divided into a plurality of sample blocks, and the sample second characteristic information includes sample second characteristic information corresponding to each sample block, the sample second characteristic information corresponding to each sample block including sample first characteristic coefficients and sample second characteristic coefficients corresponding to the sample block, the sample first characteristic coefficients being related to physical field absorption characteristics and physical field reflection characteristics of a sample sub-region in the sample scanning room corresponding to the sample block, and the sample second characteristic coefficients being related to a position and a size of the sample block.

4. The method of claim 3, wherein, The physical field simulation model includes an input layer, a first part, a second part and an output layer connected in sequence, wherein, 5. The method of claim 1, wherein, the first part includes at least two first layers connected in sequence, the number of nodes in the at least two first layers decreases in sequence, a first layer containing the largest number of nodes in the first part is connected to the input layer, and a first layer containing the smallest number of nodes is connected to the second part; and the second part includes at least two second layers connected in sequence, the number of nodes in the at least two second layers increases in sequence, a second layer containing the smallest number of nodes in the second part is connected to the first part, and a second layer containing the largest number of nodes in the second part is connected to the output layer. further comprising:

6. The method of claim 1, wherein, ​ constructing a three-dimensional virtual space of the scan room based on a physical field distribution in the scan room when the magnetic resonance instrument is in operation, the three-dimensional virtual space presenting relevant information of at least two objects in the scan room and the physical field distribution; and displaying the three-dimensional virtual space by a virtual reality device.

7. The method of claim 6, wherein, The three-dimensional virtual space includes a ground model corresponding to a ground of the scan room, The constructing a three-dimensional virtual space of the scan room based on a physical field distribution in the scan room when the magnetic resonance instrument is in operation includes: dividing the scan room into at least two regions extending along a height direction; determining a maximum physical field in each region of the at least two regions based on the physical field distribution; generating the ground model based on the maximum physical field of each region, the ground model presenting a physical field contour map corresponding to the maximum physical field.

8. The method of claim 7, wherein, Along a target direction, the scan room is divided into multiple layers, and each layer corresponds to a physical field contour in the three-dimensional virtual space.

9. A magnetic resonance physical field simulation system, comprising: a first acquisition module configured to acquire a three-dimensional space model of a scan room in which a magnetic resonance instrument is located; a second acquisition module configured to acquire first characteristic information of the magnetic resonance instrument, the first characteristic information including at least a physical field emission model of the magnetic resonance instrument; and a determination module configured to: acquire reference information; divide the three-dimensional space model into at least two blocks of different sizes based on the reference information, the reference information including an activity range of a user in the scan room and / or a position of a device that is damaged with a probability greater than a threshold under a physical field emitted by the magnetic resonance instrument; acquire second characteristic information corresponding to each block of the at least two blocks, the second characteristic information including first characteristic coefficients and second characteristic coefficients, the first characteristic coefficients being related to physical field absorption characteristics and physical field reflection characteristics of a sub-region in the scan room corresponding to the block, and the second characteristic coefficients being related to a position and a size of the block; and determine a physical field distribution in the scan room when the magnetic resonance instrument is in operation by using a physical field simulation model based on the second characteristic information of the at least two blocks and the first characteristic information.

10. A magnetic resonance physical field simulation method, comprising: acquiring a three-dimensional space model of a scan room in which a magnetic resonance instrument is located; acquiring first characteristic information of the magnetic resonance instrument, the first characteristic information including at least a physical field emission model of the magnetic resonance instrument; and acquiring reference information; dividing the three-dimensional space model into at least two blocks of different sizes based on the reference information, the reference information including an activity range of a user in the scan room and / or a position of a device that is damaged with a probability greater than a threshold under a physical field emitted by the magnetic resonance instrument; acquiring second characteristic information corresponding to each block of the at least two blocks, the second characteristic information including first characteristic coefficients and second characteristic coefficients, the first characteristic coefficients being related to physical field absorption characteristics and physical field reflection characteristics of a sub-region in the scan room corresponding to the block, and the second characteristic coefficients being related to a position and a size of the block; and determining a physical field distribution in the scan room when the magnetic resonance instrument is in operation by using a physical field simulation model based on the second characteristic information of the at least two blocks and the first characteristic information.

Images