Method and apparatus for self-checking of a magnetic resonance coil, computer device and medium

Abstract

The application relates to a self-checking method and device of a magnetic resonance coil, computer equipment and a medium. The method comprises the following steps: acquiring a magnetic resonance pre-scan signal; determining a first input parameter of a self-checking model according to at least one of a noise signal in the magnetic resonance pre-scan signal and a magnetic resonance signal subjected to a radio frequency pulse; and inputting the first input parameter into the self-checking model to obtain self-checking information of the magnetic resonance coil. The self-checking method of the magnetic resonance coil provided by the application can reduce the self-checking period of the magnetic resonance coil and improve the self-checking efficiency of the magnetic resonance coil.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of magnetic resonance imaging, and in particular to a self-checking method and device of a magnetic resonance coil, a computer device, a storage medium and a computer program product. BACKGROUND

[0002] When performing magnetic resonance imaging using a magnetic resonance device, the magnetic resonance signals corresponding to the object to be detected are mainly obtained through a magnetic resonance coil for imaging. The damage of the magnetic resonance coil will affect the quality of the magnetic resonance image, and therefore it is necessary to monitor whether the magnetic resonance coil is normal.

[0003] In the conventional technology, whether the magnetic resonance coil is normal is mainly determined based on the signal-to-noise ratio of each channel image of the magnetic resonance coil and a threshold value. However, it takes a certain time to obtain each channel image of the magnetic resonance coil, and the self-checking period of the magnetic resonance coil is long, resulting in a low self-checking efficiency of the magnetic resonance coil. SUMMARY

[0004] Therefore, it is necessary to provide a self-checking method and device of a magnetic resonance coil, a computer device, a storage medium and a computer program product to solve the above technical problems.

[0005] In a first aspect, an embodiment of the present application provides a self-checking method of a magnetic resonance coil, comprising:

[0006] obtaining a magnetic resonance pre-scan signal received by the magnetic resonance coil, the magnetic resonance pre-scan signal comprising a noise signal and a magnetic resonance signal generated after a radio frequency pulse excitation;

[0007] determining a first input parameter of a self-checking model according to at least one of the noise signal and the magnetic resonance signal;

[0008] inputting the first input parameter into the self-checking model to obtain self-checking information of the magnetic resonance coil.

[0009] In one of the embodiments, the magnetic resonance coil comprises a plurality of receiving channels, and the self-checking information of the magnetic resonance coil comprises at least one of a number of the receiving channels that have failed, a type of failure and a level of failure.

[0010] In one of the embodiments, the determination of the first input parameter of the self-checking model according to at least one of the noise signal and the magnetic resonance signal comprises:

[0011] obtaining magnetic resonance coil attribute information, the magnetic resonance coil attribute information comprising at least one of a coil size, a coil material, a coil category, and a number of receiving channels included in the coil;

[0012] inputting the magnetic resonance coil information and one of the noise signal and the magnetic resonance signal as the first input parameter.

[0013] In one embodiment, the self-checking model includes a first fault determination model and a second fault determination model, the first input parameter is input into the self-checking model to obtain self-checking information of the magnetic resonance coil, including:

[0014] The first input parameter is input into the first fault determination model to obtain a fault determination result, the fault determination result includes whether the magnetic resonance coil has a fault and a receiving channel number of the fault;

[0015] According to the fault determination result, a second input parameter of the second fault determination model is determined, and the second input parameter is input into the second fault determination model to obtain a type of the fault and a level of the fault.

[0016] In one embodiment, according to the fault determination result, the second input parameter of the second fault determination model is determined, including:

[0017] If the fault determination result is that the magnetic resonance coil has a fault, the second input parameter is determined according to at least one of the noise signal and the magnetic resonance signal corresponding to the receiving channel number of the fault.

[0018] In one embodiment, the type of the fault includes at least one of the following: a loop disconnection of the magnetic resonance coil, a frequency offset of the magnetic resonance coil, and a receiving chain disconnection of the magnetic resonance coil.

[0019] In a second aspect, one embodiment of the present application provides a self-checking device of a magnetic resonance coil, including:

[0020] The acquisition module is configured to acquire a magnetic resonance pre-scan signal received by the magnetic resonance coil, the magnetic resonance pre-scan signal including a noise signal and a magnetic resonance signal generated after a radio frequency pulse excitation;

[0021] The first determination module is configured to determine a first input parameter of a self-checking model according to at least one of the noise signal and the magnetic resonance signal;

[0022] The second determination module is configured to input the first input parameter into the self-checking model to obtain self-checking information of the magnetic resonance coil.

[0023] In a third aspect, one embodiment of the present application provides a computer device including a memory and a processor, the memory stores a computer program, and the processor implements the steps of the method provided in the above embodiments when executing the computer program.

[0024] In a fourth aspect, one embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the method provided in the above embodiments.

[0025] In a fifth aspect, an embodiment of the present application further provides a computer program product, comprising a computer program, wherein the computer program is processed to implement the steps of the method provided by the above-mentioned embodiment when executed.

[0026] The embodiment of the present application provides a self-checking method and device of a magnetic resonance coil, a computer device, a storage medium and a computer program product. The method comprises the following steps: acquiring a magnetic resonance pre-scan signal received by the magnetic resonance coil; determining a first input parameter of a self-checking model according to at least one of noise signals in the magnetic resonance pre-scan signal and magnetic resonance signals generated after a radio frequency pulse excitation, and inputting the first input parameter into the self-checking model to obtain self-checking information of the magnetic resonance coil. The self-checking method of the magnetic resonance coil provided by the embodiment of the present application does not need to acquire images of each receiving channel of the magnetic resonance coil, reduces the self-checking period of the magnetic resonance coil, and thus the self-checking efficiency of the magnetic resonance coil can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0028] Figure 1 An application environment diagram of the self-checking method of the magnetic resonance coil provided by an embodiment;

[0029] Figure 1A A structural schematic diagram of the magnetic resonance device provided by an embodiment;

[0030] Figure 2 A step flowchart of the self-checking method of the magnetic resonance coil provided by an embodiment;

[0031] Figure 3 A step flowchart of the self-checking method of the magnetic resonance coil provided by another embodiment;

[0032] Figure 4 A step flowchart of the self-checking method of the magnetic resonance coil provided by another embodiment;

[0033] Figure 5 A noise distribution diagram of the magnetic resonance coil provided by an embodiment;

[0034] Figure 6 A display interface of a display provided by an embodiment;

[0035] Figure 7 A display interface of a display provided by another embodiment;

[0036] Figure 8 A self-test log diagram provided for one embodiment;

[0037] Figure 9 A schematic diagram of the structure of a self-testing device for a magnetic resonance coil provided in one embodiment;

[0038] Figure 10 A schematic diagram of the structure of a computer device provided in one embodiment. Detailed Implementation

[0039] To make the above-mentioned objectives, features, and advantages of this application more apparent and understandable, the specific embodiments of this application are described in detail below with reference to the accompanying drawings. Many specific details are set forth in the following description to provide a thorough understanding of this application. However, this application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar modifications without departing from the spirit of this application. Therefore, this application is not limited to the specific embodiments disclosed below.

[0040] The serial numbers assigned to components in this article, such as "first" and "second", are used only to distinguish the objects being described and have no sequential or technical meaning.

[0041] The self-testing method for magnetic resonance coils provided in this application embodiment can be applied to, for example... Figure 1 The application scenario shown includes a terminal 110 and an magnetic resonance imaging (MRI) device 111, wherein the terminal 110 can communicate with the MRI device 111 via a network. The terminal 110 can be, but is not limited to, various personal computers, laptops, and tablets.

[0042] Please see Figure 1A , Figure 1A This is a schematic diagram of a magnetic resonance device 111 provided in an embodiment of this application.

[0043] In the embodiment, the magnetic resonance device 111 comprises a scanner 101, a patient bed 102, and a magnetic resonance coil 103. The scanner 101 is configured to perform medical imaging (to perform a scanning imaging operation) on a subject to be scanned, the patient bed 102 is configured to carry the subject to be scanned, and the magnetic resonance coil 103 is a local receiving coil or a transceiving integrated coil and is placed on the surface of the body of the subject during a scanning process. For example, the patient bed 102 can extend in a front-rear direction and a left-right direction. The front-rear direction is the length direction of the patient bed 102, and the left-right direction is the width direction of the patient bed 102. The subject to be scanned can be placed on the surface of the patient bed 102 and moved along the front-rear direction or the left-right direction with the patient bed 102 or moved in an up-down direction. For example, the scanner 101 can form a hole with a certain size. The diameter of the hole can be greater than or equal to the size of the patient bed 102 in the width direction. Alternatively, the subject to be scanned can be in a supine position, a left lateral position, a right lateral position, a prone position, or the like on the patient bed.

[0044] In the present application, the “patient bed” can represent the same meaning as and can be replaced by “couch”, “scanning bed”, “supporting table”, “supporting bed”, “examination bed”, and the like, which represent the structure for carrying the subject to be scanned. In the present application, the “scanner” can represent the same meaning as and can be replaced by “scanning device”, “scanning system”, “scanning apparatus”, “image scanning device”, and “imaging device”. The subject to be scanned can represent a human body, an animal body, a water phantom, and other living or non-living bodies.

[0045] The scanner 101 mainly comprises a main magnet, gradient coils, a body coil, a spectrometer system, a controller, and the like. The main magnet is a superconducting magnet, which is configured to generate a main magnetic field (B0 field). The main magnet surrounds a detection space, and water molecules in the body of the subject to be scanned can form a Larmor frequency (also referred to as a precession frequency or a system center frequency) in the main magnetic field. The patient bed 102 is placed in the detection space and can carry the subject to be scanned to move relative to the main magnet. The gradient coils comprise X gradient coils, Y gradient coils, and Z gradient coils, which are configured to generate X-direction gradient fields, Y-direction gradient fields, and Z-direction gradient fields, respectively, to generate corresponding spatial encoding signals, so as to spatially position the magnetic resonance signals. The body coil is configured to emit a radio frequency pulse signal to the subject to be scanned, and the radio frequency pulse signal can excite the nuclear spins in the body of the subject to be scanned. It can be understood that the body coil can also have a receiving function and can receive the spin signals excited by the subject to be scanned. Alternatively, the types of the body coil or the local coil can be a birdcage coil, a solenoid coil, a saddle coil, a Helmholtz coil, an array coil, a loop coil, and the like.

[0046] Exemplarily, the scanner 101 is externally provided with a gantry, and the gantry is a ring-shaped gantry, and the ring-shaped gantry internally includes a main magnet, a gradient coil and a body coil (not shown in the figure). The space inside the ring-shaped gantry is a detection space, that is, the shell, the main magnet, the gradient coil and the body coil jointly form a hole cavity extending along the length direction of the bed 102, and the space contained in the hole cavity is the detection space. The detection space is the intermediate space region between the front port portion and the rear port portion of the hole cavity, and the intermediate space region can be arranged in the central region of the main magnet. The imaging effect of the central region of the main magnet is better than that of the port regions on both sides.

[0047] The magnetic resonance coil 103 can be arranged as an array coil, and the array coil can be arranged in a 4-channel mode, an 8-channel mode, a 16-channel mode, a 24-channel mode or a 32-channel mode. Exemplarily, the magnetic resonance coil 103 can be movably arranged on the surface of the bed 102 or the body of the object. In an embodiment, the magnetic resonance coil 103 can be placed on the surface of the chest of the object and attached to the human body by a bandage or a magic tape for performing a cardiac scan of the object. The magnetic resonance coil 103 has different categories. Optionally, the categories of the magnetic resonance coil can be divided according to the corresponding parts of the magnetic resonance coil and the number of coil channels. For example, the categories of the magnetic resonance coil can include a head coil, a spine coil, an abdominal coil, an ankle coil, a wrist coil, a head-neck combined coil, a cervical-thoracic coil, a lower limb coil, a knee joint coil and the like. Further, the head coil can be further divided into a 16-channel head coil, a 32-channel head coil, a 64-channel head coil and a 128-channel head coil.

[0048] The gantry of the scanner 101 is provided with a display 104 connected with the controller of the terminal, for displaying the working state of the magnetic resonance device, the information of the scanned object and the protocol selected by the doctor and the like. It can be understood that the display 104 can also be connected with the scanner 101 through a wired or wireless connection to receive the magnetic resonance signals collected by the magnetic resonance coil 103; or the display 104 is connected with the controller of the magnetic resonance device to receive the cardiac motion curve or signal obtained by processing in the controller. Exemplarily, the working state of the magnetic resonance device can be one or more of the following: a scanning sequence being executed, a state of the magnet running, a state of the gradient running, a scanning time, a specific specific absorption rate of the human body, self-checking information of the magnetic resonance coil 103 and the like. The information of the scanned object can be one or more of the following: the height, the weight, the gender, the part to be scanned of the scanned object and the respiratory motion state, the cardiac motion state of the scanned object and the like. The protocol selected by the doctor can be displayed in the form of a list or a human figure or in a mixed form of the two.

[0049] The technical solutions of the present application and how the technical solutions solve the technical problems will be described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes can not be described again in some embodiments. The embodiments of the present application will be described below with reference to the drawings.

[0050] In one embodiment, referring to Figure 2 , one embodiment of the present application provides a self-checking method for a magnetic resonance coil. The method is applied to a terminal in Figure 1 for example, and includes the following steps:

[0051] Step 200: Obtain a magnetic resonance pre-scan signal received by the magnetic resonance coil. The magnetic resonance pre-scan signal includes a noise signal and a magnetic resonance signal generated after a radio frequency pulse is excited.

[0052] The magnetic resonance pre-scan signal can be a signal scanned by using a magnetic resonance device before a formal imaging scan is performed on a to-be-detected object, or can be a signal collected when the magnetic resonance device is calibrated. The magnetic resonance signal generated after the radio frequency pulse is excited can include one or more of a free induction decay signal (FID), a spin echo (SE) signal, and a stimulated echo (STE) signal.

[0053] The to-be-detected object receives excitation of a certain radio frequency pulse such as a 90° pulse, and a macroscopic transverse magnetization vector is generated in the tissue of the to-be-detected object. After the radio frequency pulse is turned off, the macroscopic transverse magnetization vector in the tissue decays in an exponential form due to the influence of T2 relaxation and the inhomogeneity of the main magnetic field, that is, free induction decay. In the embodiment of the present application, the free induction decay signal can be obtained by directly recording the free induction decay of the transverse magnetization vector by using the magnetic resonance coil.

[0054] The 90° radio frequency pulse generates a macroscopic transverse magnetization vector. After the 90° radio frequency pulse is turned off, the proton group is out of phase due to the inhomogeneity of the main magnetic field, and the macroscopic transverse magnetization vector in the tissue gradually decays. A 180° aggregation pulse is applied at a subsequent time, the proton group gradually rephases, the macroscopic transverse magnetization vector in the tissue reaches a maximum value, and then the proton group gradually loses phase again, and the macroscopic transverse magnetization vector in the tissue gradually decays again. By recording the change process of the macroscopic transverse magnetization vector by using the magnetic resonance coil, a spin echo can be obtained.

[0055] The stimulated echo is obtained by using a stimulated echo acquisition mode (STEAM). The STEAM is composed of three 90° selection pulses, each of which is applied to the tissue of the subject to be detected in the presence of a quadrature gradient, so that a stimulated echo signal is generated in a voxel at the intersection of the three layers. The first 90° excitation pulse excites all the nuclear protons in the selected layer in cooperation with the layer selection gradient; the magnetization vector in the XY plane is flipped and located in the XZ plane under the action of the second 90° RF pulse; and the third selective 90° pulse excitation flips all the nuclear protons into the XY plane and again rephases after a TE / 2 time to form an echo.

[0056] The noise signal includes background noise, that is, a signal that interferes with the effective signal in the magnetic resonance signal. The noise signal can be a noise signal after the radio frequency pulse is applied, or a noise signal when the radio frequency pulse is not applied. The noise signal can represent the standard deviation of the signal intensity of the same number of pixels in the region of interest. For example, the noise signal can come from the signal of the region outside the anatomical structure of interest, which can deteriorate the quality of the magnetic resonance image and the parameter mapping. In this embodiment, the noise signal is an empty signal obtained by only implementing the gradient pulse without applying the radio frequency pulse. The terminal obtains the magnetic resonance pre-scan signal, which can be directly stored in the memory of the terminal, and can be directly obtained in the memory of the terminal when the terminal needs to obtain it. The specific method of obtaining the magnetic resonance pre-scan signal is not limited in this embodiment, as long as the function can be realized.

[0057] Step 210, determining the first input parameter of the self-checking model according to at least one of the noise signal and the magnetic resonance signal.

[0058] The self-checking model can be a model obtained by training a neural network model in advance by using a training sample. The self-checking model is used to obtain the self-checking signal of the magnetic resonance coil. The training sample can be a plurality of signals same as the magnetic resonance pre-scan signal. The description of the training sample can refer to the specific description of the magnetic resonance pre-scan signal described above. The specific process of determining the self-checking model obtained by training is not limited in this embodiment, as long as the function can be realized.

[0059] The terminal determines the first input parameter of the self-checking model according to at least one of the obtained noise signal and the magnetic resonance signal. In other words, the terminal can determine the first input parameter according to any one or more of the noise signal and the magnetic resonance signal. At the same time, the terminal can also determine the first input parameter from any one or more of FID, SE and STE. The specific method of determining the first input parameter is not limited in this embodiment, as long as the function can be realized.

[0060] In step 220, the first input parameter is input into the self-checking model to obtain self-checking information of the magnetic resonance coil.

[0061] The self-checking information of the magnetic resonance coil can represent a quality assurance (QA) index of the magnetic resonance coil. The self-checking information of the magnetic resonance coil can include information about whether the magnetic resonance coil can normally work and other information about the magnetic resonance coil. After obtaining the first input parameter, the terminal inputs the first input parameter into the pre-trained self-checking model, and the self-checking model can output the self-checking information of the magnetic resonance coil. The present embodiment is not limited to specific self-checking information of the magnetic resonance coil, as long as the function thereof can be realized.

[0062] The self-checking method of the magnetic resonance coil provided in the present embodiment can obtain a magnetic resonance pre-scan signal received by the magnetic resonance coil, determine a first input parameter of a self-checking model according to at least one of a noise signal in the magnetic resonance pre-scan signal and a magnetic resonance signal, and input the first input parameter into the self-checking model to obtain self-checking information of the magnetic resonance coil. The self-checking method of the magnetic resonance coil provided in the present embodiment does not need to obtain images of each channel of the magnetic resonance coil, reduces the self-checking period of the magnetic resonance coil, and thus can improve the self-checking efficiency of the magnetic resonance coil. Moreover, the self-checking method of the magnetic resonance coil provided in the present embodiment can perform real-time self-checking on the magnetic resonance coil, can timely find a malfunctioning magnetic resonance coil, and enables a maintenance personnel to timely maintain the coil, and thus has high practicability and reliability.

[0063] In one embodiment, a possible implementation manner of determining the first input parameter of the self-checking model according to at least one of the noise signal and the magnetic resonance signal includes:

[0064] One or more of the noise signal and the magnetic resonance signal are taken as the first input parameter.

[0065] After obtaining the magnetic resonance pre-scan signal, the terminal can take any one or more of the noise signal and the magnetic resonance signal in the magnetic resonance pre-scan signal as the first input parameter. In other words, the terminal can directly take any one of the noise signal and the magnetic resonance signal as the first input parameter, can take the noise signal in combination with any one of FID, SE and STE as the first input parameter, and can directly take the noise signal and FID, SE and STE as the first input parameter, and can also take any one or more of FID, SE and STE as the first input parameter.

[0066] In the present embodiment, the first input parameter can be one or more of the noise signal and the magnetic resonance signal, and a user can select it according to an actual scene, so that the self-checking method of the magnetic resonance coil has high practicability.

[0067] In one embodiment, the magnetic resonance coil comprises a plurality of receiving channels, and the self-checking information of the magnetic resonance coil comprises at least one of a number of a failed receiving channel, a type of failure, and a level of failure.

[0068] The magnetic resonance coil comprises a plurality of receiving channels, that is, the magnetic resonance pre-scan signal received by the magnetic resonance coil comprises a magnetic resonance pre-scan signal received by each receiving channel, and then the terminal can perform self-checking on the corresponding receiving channel according to the magnetic resonance pre-scan signal received by each receiving channel to obtain self-checking information of each receiving channel in the magnetic resonance coil. Each receiving channel of the magnetic resonance coil is provided with a number, and when the magnetic resonance coil has a fault, the self-checking information obtained by the self-checking method provided by the present application can include the number of the receiving channel that has a fault, the type of failure of the receiving channel, and the level of failure of the receiving channel. The level of failure refers to the severity of the failure of the receiving channel. The present embodiment does not limit the number of receiving channels of the magnetic resonance coil and the specific content of the self-checking information, as long as the functions can be realized.

[0069] In one embodiment, as shown in Figure 3 a possible implementation of determining the first input parameter of the self-checking model according to at least one of the noise signal and the magnetic resonance signal, the steps comprise:

[0070] Step 300, obtaining magnetic resonance coil attribute information, the magnetic resonance coil information comprising at least one of coil size, coil material, coil category, and the number of receiving channels contained by the coil.

[0071] The coil size can refer to the size of the coil and the number of turns of the coil. The number of receiving channels contained by the coil refers to the number of receiving channels included in the magnetic resonance coil information. The specific description of the coil category can refer to the description in the above embodiments, which will not be described here. The magnetic resonance coil attribute information can be directly stored in the memory of the terminal, and the terminal can directly obtain it when needed. The present embodiment does not limit the method of obtaining the magnetic resonance coil attribute information, as long as the functions can be realized.

[0072] The magnetic resonance coil attribute information can be directly obtained by the staff during installation of the magnetic resonance device and stored in the memory of the terminal, or it can be obtained during self-checking of the magnetic resonance coil and stored in the memory of the terminal.

[0073] Step 310, taking the magnetic resonance coil attribute information and at least one of the noise signal and the magnetic resonance signal as the first input parameter.

[0074] After obtaining the magnetic resonance coil attribute information, the terminal takes the magnetic resonance coil attribute information and at least one of the noise signal and the magnetic resonance signal as the first input parameter. In other words, the terminal can take any one of the magnetic resonance coil attribute information, the noise signal and the magnetic resonance signal as the first input parameter, or take both the noise signal and the magnetic resonance signal as the first input parameter; or take any one or more of the FID, SE and STE in the magnetic resonance signal as the first input parameter.

[0075] In the embodiment, the magnetic resonance coil attribute information is added in the first input parameter, which can improve the accuracy of the self-check information determination of the magnetic resonance coil.

[0076] In one embodiment, as shown in FIG. 4, the self-check model includes a first fault determination model and a second fault determination model. One possible implementation of inputting the first input parameter into the self-check model to obtain the self-check information of the magnetic resonance coil includes the following steps. Figure 4

[0077] Step 400: inputting the first input parameter into the first fault determination model to obtain a fault determination result; the fault determination result includes whether the magnetic resonance coil has a fault and the receive channel number of the fault.

[0078] The self-check model can be composed of the first fault determination model and the second fault determination model. The first fault determination model can be obtained by training a neural network model with the same training sample as the first input parameter. The training process of the first fault determination model is not limited in the embodiment, as long as it can realize its function.

[0079] The terminal inputs the first input parameter into the pre-trained first fault determination model, and the first fault determination model outputs the fault determination result of the magnetic resonance coil determined according to the first input parameter. Specifically, the first fault determination model can determine whether the magnetic resonance coil has a fault, and when the magnetic resonance coil has a fault, the receive channel number of the fault in the magnetic resonance coil can be obtained.

[0080] In one optional embodiment, if it is determined by the first fault determination model that the magnetic resonance coil has no fault, the output of the first fault model is {-1}, and if it is determined by the first fault determination model that the magnetic resonance coil has a fault and the receive channel number of the fault is 10, the output of the first fault model is {10}.

[0081] Step 410: determining the second input parameter of the second fault determination model according to the fault determination result, inputting the second input parameter into the second fault determination model to obtain the fault type of the magnetic resonance coil and the fault level of the magnetic resonance coil. ​

[0082] The terminal can determine the input parameter of the second fault determination model, i.e., the second input parameter, according to the fault determination result output by the first fault determination model. The terminal inputs the determined second input parameter into the second fault determination model, and can obtain the type and level of the fault of the magnetic resonance coil. That is, the type and level of the fault of the magnetic resonance coil can be determined by the second fault determination model. The embodiment does not limit the specific process of determining the second input parameter according to the fault determination result, as long as the function can be realized.

[0083] Each receiving channel of the magnetic resonance coil is provided with a corresponding number. According to the embodiment, the first fault determination model can not only determine whether the magnetic resonance coil has a fault, but also determine the specific receiving channel number of the fault when the magnetic resonance coil has a fault. The second fault determination model can further determine the type and level of the fault, so that the staff can timely obtain the specific receiving channel, fault type and fault level of the fault, and can timely perform corresponding maintenance or replacement operation, thereby improving the reliability of the magnetic resonance coil.

[0084] In one embodiment, a possible implementation of determining the second input parameter of the second fault determination model according to the fault determination result is involved, and the steps include:

[0085] If the fault determination result is that the magnetic resonance coil has a fault, the second input parameter is determined according to at least one of the noise signal and the magnetic resonance signal corresponding to the receiving channel number of the fault of the magnetic resonance coil.

[0086] If the fault determination result output by the first fault determination model is that the magnetic resonance coil has a fault, the terminal obtains the magnetic resonance pre-scan signal corresponding to the receiving channel number of the fault in the fault determination result. The second input parameter is determined according to any one or more of the noise signal and the magnetic resonance signal in the magnetic resonance pre-scan signal.

[0087] Optionally, the terminal can take any one of the noise signal and the magnetic resonance signal corresponding to the receiving channel number of the fault as the second input parameter; the terminal can also take both the noise signal and the magnetic resonance signal corresponding to the receiving channel number of the fault as the second input parameter; and the terminal can also take any one or more of FID, SE and STE in the magnetic resonance signal corresponding to the receiving channel number of the fault as the second input parameter.

[0088] If the fault determination result output by the first fault determination model is that the magnetic resonance coil has no fault, the terminal can set the second input parameter as empty.

[0089] Specifically, a first correspondence relationship between different types of faults and corresponding numbers of the different types of faults, and a second correspondence relationship between different levels of faults and corresponding numbers of the different levels of faults are included in the memory of the terminal. The output of the second fault determination model is {1, 3}, 1 represents a corresponding number of a type of fault occurring in the magnetic resonance coil, and 3 represents a level of the fault occurring in the magnetic resonance coil. Through the corresponding number of the type of fault and the first correspondence relationship, a specific type of fault occurring in the magnetic resonance coil can be obtained. Through the corresponding number of the level of the fault and the second correspondence relationship, a specific level of the fault occurring in the magnetic resonance coil can be obtained.

[0090] In one embodiment, the type of fault includes at least one of a loop disconnection of the magnetic resonance coil, a frequency offset of the magnetic resonance coil, and a receive chain disconnection of the magnetic resonance coil.

[0091] Specifically, the self-checking model can identify the loop disconnection of the magnetic resonance coil, the receive chain disconnection, and other types of faults through the noise signal. For example, the loop disconnection of the magnetic resonance coil can be caused by a soft board fracture; the disconnection of the receive chain can be caused by a failure of an amplifier connected to the loop, damage to a connection pin of the magnetic resonance coil, a cable disconnection, and other front-end faults.

[0092] The frequency offset fault of the magnetic resonance coil can be identified by using the magnetic resonance pre-scan signal collected in the calibration stage before the imaging scan. For example, the coil frequency offset fault can be caused by damage to a capacitor included in the magnetic resonance coil, a diode failure, and the like.

[0093] In one embodiment, the self-checking method of the magnetic resonance coil further includes: establishing a coil noise database according to noise data collected under normal (no fault) conditions of each type of magnetic resonance coil.

[0094] In one embodiment, the self-checking model automatically retrieves noise probability distribution data corresponding to the coil noise database, fits a Weibull probability distribution, combines the noise distribution data actually collected from each receiving channel, establishes a two-dimensional probability distribution space, and distinguishes between normal and faulty coil channels. In this embodiment, the self-checking model includes an SVM1 classifier and an SVM2 classifier based on support vector machines. Both the SVM1 classifier and the SVM2 classifier can be used to distinguish between normal coil receiving channels and faulty coil receiving channels after being trained. It is assumed that the SVM1 classifier is used to distinguish between whether a magnetic resonance coil has a loop breakage fault of the magnetic resonance coil, and the SVM2 classifier is used to distinguish between whether a magnetic resonance coil has a receiving link breakage fault of the magnetic resonance coil. Specifically, the SVM1 classifier and the SVM2 classifier automatically determine the noise distribution area of each receiving channel in the two-dimensional probability distribution space. When the noise distribution is in the first (upper left corner) area of the SVM2 classifier, it is determined to be a “magnetic resonance coil receiving link fault”. When the noise distribution is in the second (lower right corner) area of the SVM1 classifier, it is determined to be a “magnetic resonance coil loop breakage”.

[0095] The noise distribution of each receiving channel of the magnetic resonance coil is as shown in Figure 5 Figure 5 The horizontal coordinate represents the noise distribution actually collected from each receiving channel of the magnetic resonance coil, and the vertical coordinate represents the noise distribution of each receiving channel of the magnetic resonance coil under normal circumstances. For each receiving channel under normal circumstances, fitting a Weibull probability distribution will obtain a reference two-dimensional probability distribution line (in this embodiment, the coil includes multiple receiving channels, corresponding to a set of two-dimensional probability distribution lines) through a 45° angle of the origin, as represented by A in Figure 5 According to the reference two-dimensional probability distribution line of the magnetic resonance coil under normal circumstances, a first decision boundary (B1 in the figure, plotted by data1) and a second decision boundary (B2 in the figure, plotted by data2) are determined. The first decision boundary formed by the SVM1 classifier can output “magnetic resonance coil receiving link breakage fault” according to curve C1. The second decision boundary formed by the SVM2 classifier can output “magnetic resonance coil loop breakage fault” according to curve D1.

[0096] In one embodiment, the fault level can be determined according to the distance between the two-dimensional probability distribution line corresponding to the current magnetic resonance coil and the reference two-dimensional probability distribution line. For example, the smaller the distance between the two-dimensional probability distribution line corresponding to the current magnetic resonance coil and the reference two-dimensional probability distribution line, the lower the fault level, i.e., the closer the current magnetic resonance coil to normal; the greater the distance between the two-dimensional probability distribution line corresponding to the current magnetic resonance coil and the reference two-dimensional probability distribution line, the higher the fault level, i.e., the more serious the fault of the current magnetic resonance coil. ​

[0097] Considering that there are differences in the regular distribution of noise collected by the coil in different system environments, in an embodiment, different coil noise databases can be established for different magnetic resonance systems according to different main magnetic field strengths. For example, a coil noise database corresponding to a 1.5T main magnetic field, a coil noise database corresponding to a 3.0T main magnetic field, a coil noise database corresponding to a 5.0T main magnetic field, and the like can be established respectively.

[0098] In an embodiment, an interactive interface on the display of the terminal (as shown in Figure 6 A QA button can be set on the interactive interface. The QA button can be used to turn on or turn off the self-checking function. For a clinical scenario, turning on the QA button can identify whether the magnetic resonance coil is abnormal, and a warning dialog box (as shown in Figure 7 Further, the abnormal information of the magnetic resonance coil can be recorded in a log folder, so as to facilitate engineers to debug coil failures. For a research scenario, the QA button can be set to be turned on by default. The coil abnormality pops up a warning dialog box, and the customer can choose whether to continue scanning. In addition, the display of the terminal can also display a toolbox for viewing the abnormal information of the magnetic resonance coil, that is, the toolbox stores the self-checking information of the magnetic resonance coil that has failed.

[0099] Specifically, there are two methods for self-checking the magnetic resonance coil. Scheme one, the coil QA button under the system tab in the interactive interface on the display is turned on, and after detecting that the receiving channel of the magnetic resonance coil is abnormal, a warning dialog box is popped up to prompt whether to continue scanning. Clicking “Confirm” continues the scanning, clicking “Cancel” stops the scanning, and clicking “No longer display” continues the scanning and does not remind before the end of the current scanning. The interactive interface can also set an adaptive toolbox, and authorized research users can view the coil self-checking log file (self-checking information) in the adaptive toolbox.

[0100] Scheme two, the coil QA button under the system tab is turned on, and after detecting that the receiving channel of the magnetic resonance coil is abnormal, a warning appears in the system manager interface in the display to prompt whether to continue scanning.

[0101] In an embodiment, in an actual application scenario, the bed is lowered, the magnetic resonance coil is replugged, and the coil unit is reselected, which will activate the coil QA program. The coil QA program will compare whether the existing magnetic resonance coil name and the historical record magnetic resonance coil name are consistent. If not, the coil QA program is activated, otherwise the coil QA link is skipped.

[0102] When the coil QA program is activated, the terminal searches for a magnetic resonance pre-scan signal, performs a QA function according to the magnetic resonance pre-scan signal, and records a log, marking the test time. A warning window is popped up when the magnetic resonance coil is abnormal, reminding the user whether to stop scanning.

[0103] In one embodiment, the log is recorded as shown in Figure 8 , wherein the timestamp refers to the time of self-checking of the magnetic resonance coil, KNC1 represents the type of the magnetic resonance coil, and the number after the type of the magnetic resonance coil represents the receiving channel number of the magnetic resonance coil, and the state represents the state of self-checking of the magnetic resonance coil.

[0104] In a specific embodiment, if the free induction decay signal decreases and the noise signal significantly increases, it indicates that the loop of the magnetic resonance coil is disconnected; if the free induction decay signal decreases and the noise signal increases slightly, it indicates that the frequency of the magnetic resonance coil is offset; and if the free induction decay signal disappears and the noise signal decreases significantly, it indicates that the receiving link of the magnetic resonance coil is disconnected.

[0105] It should be understood that although each step in the flowchart in the figure is shown in sequence following the arrows, the steps are not necessarily executed in the order indicated by the arrows. Unless otherwise explicitly stated herein, there is no strict order requirement for the execution of the steps, and the steps can be executed in other orders. Moreover, at least part of the steps in the figure can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of the sub-steps or stages is not necessarily sequential, but can be alternately executed with at least part of other steps or sub-steps or stages of other steps.

[0106] Based on the same inventive concept, the embodiments of the present application also provide a magnetic resonance coil self-checking monitoring device for implementing the magnetic resonance coil self-checking monitoring method described above. The problem-solving implementation scheme provided by the device is similar to the implementation scheme described in the above method, and therefore the specific limitations in one or more magnetic resonance coil self-checking device embodiments provided below can refer to the limitations of the magnetic resonance coil self-checking method described above, which will not be described here again.

[0107] In one embodiment, referring to Figure 9 , a magnetic resonance coil self-checking device 10 is provided, which includes an acquisition module 11, a first determination module 12, and a second determination module 13. Wherein,

[0108] The acquisition module 11 is configured to acquire a magnetic resonance pre-scan signal received by a magnetic resonance coil, the magnetic resonance pre-scan signal including a noise signal and a magnetic resonance signal generated after a radio frequency pulse excitation;

[0109] The first determining module 12 is configured to determine a first input parameter of the self-checking model according to at least one of the noise signal and the magnetic resonance signal.

[0110] The second determining module 13 is configured to input the first input parameter into the self-checking model to obtain the self-checking information of the magnetic resonance coil.

[0111] In an embodiment, the magnetic resonance coil includes a plurality of receiving channels, and the self-checking information of the magnetic resonance coil includes at least one of a number of the failed receiving channel, a type of failure, and a level of failure.

[0112] In an embodiment, the first determining module 12 is specifically further configured to acquire magnetic resonance coil attribute information, the magnetic resonance coil attribute information including at least one of a coil size, a coil material, a coil category, and a number of receiving channels included in the coil; and the first determining module 12 is configured to take the magnetic resonance coil attribute information and at least one of the noise signal and the magnetic resonance signal as the first input parameter.

[0113] In an embodiment, the second determining module 13 includes a first determining unit and a second determining unit. The first determining unit is configured to input the first input parameter into a first failure determining model to obtain a failure determining result, the failure determining result including whether the magnetic resonance coil has a failure and a number of the failed receiving channel; and the second determining unit is configured to determine a second input parameter of a second failure determining model according to the failure determining result, input the second input parameter into the second failure determining model, and obtain a type of failure and a level of failure.

[0114] In an embodiment, the second determining unit is specifically configured to, if the failure determining result is that the magnetic resonance coil has a failure, determine the second input parameter according to at least one of the noise signal and the magnetic resonance signal corresponding to the number of the failed receiving channel.

[0115] In an embodiment, the type of failure includes at least one of a loop disconnection of the magnetic resonance coil, a frequency offset of the magnetic resonance coil, and a receiving chain disconnection of the magnetic resonance coil.

[0116] The above-described modules in the self-checking device of the magnetic resonance coil can be implemented wholly or partially by software, hardware, and a combination thereof. The above-described modules can be embedded in or independent of a processor in a computer device in a hardware form, or can be stored in a memory in the computer device in a software form, so as to be called and executed by a processor to perform operations corresponding to the above-described modules.

[0117] In an embodiment, a computer device is provided, which can be a server, and an internal structure diagram of the computer device can be as shown in Figure 10As shown in the figure. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The communication interface of the computer device is used for wired or wireless communication with external terminals. Wireless mode can be achieved through WIFI, mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by the processor to implement a self-checking method of a magnetic resonance coil. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0118] Those skilled in the art can understand that, Figure 10 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0119] In one embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the following steps:

[0120] Obtaining a magnetic resonance pre-scan signal received by a magnetic resonance coil, the magnetic resonance pre-scan signal comprising a noise signal and a magnetic resonance signal generated after a radio frequency pulse excitation;

[0121] Determining a first input parameter of a self-checking model according to at least one of the noise signal and the magnetic resonance signal;

[0122] Inputting the first input parameter into the self-checking model to obtain self-checking information of the magnetic resonance coil.

[0123] In one embodiment, the magnetic resonance coil comprises a plurality of receiving channels, and the self-checking information of the magnetic resonance coil comprises at least one of a number of a failed receiving channel, a type of failure and a level of failure.

[0124] In one embodiment, the processor, when executing the computer program, further implements the following steps: obtaining magnetic resonance coil attribute information, the magnetic resonance coil attribute information comprising at least one of coil size, coil material, coil type, and number of receive channels included in the secondary safety; and inputting the magnetic resonance coil attribute information and at least one of the noise signal and the magnetic resonance signal as the first input parameter.

[0125] In one embodiment, the processor, when executing the computer program, further implements the following steps: inputting the first input parameter into a first fault determination model to obtain a fault determination result; the fault determination result comprising whether the magnetic resonance coil has a fault and a receive channel number of the fault; and determining a second input parameter of a second fault determination model according to the fault determination result, inputting the second input parameter into the second fault determination model to obtain a fault type and a fault level.

[0126] In one embodiment, the processor, when executing the computer program, further implements the following steps: if the fault determination result is that the magnetic resonance coil has a fault, determining the second input parameter according to at least one of the noise signal and the magnetic resonance signal corresponding to the receive channel number of the fault.

[0127] In one embodiment, the fault type comprises at least one of a loop disconnection of the magnetic resonance coil, a frequency offset of the magnetic resonance coil, and a receive chain disconnection of the magnetic resonance coil.

[0128] In one embodiment, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program, and the computer program, when executed by a processor, implements the following steps:

[0129] obtaining a magnetic resonance pre-scan signal received by a magnetic resonance coil, the magnetic resonance pre-scan signal comprising a noise signal and a magnetic resonance signal generated after a radio frequency pulse excitation;

[0130] determining a first input parameter of a self-checking model according to at least one of the noise signal and the magnetic resonance signal;

[0131] inputting the first input parameter into the self-checking model to obtain self-checking information of the magnetic resonance coil.

[0132] In one embodiment, the magnetic resonance coil comprises a plurality of receive channels, and the self-checking information of the magnetic resonance coil comprises at least one of a receive channel number of the fault, a fault type, and a fault level.

[0133] In one embodiment, the computer program, when executed by the processor, further implements the following steps: obtaining magnetic resonance coil attribute information, the magnetic resonance coil attribute information comprising at least one of coil size, coil material, coil material, coil category, and number of receiving channels included in the coil; and inputting the magnetic resonance coil attribute information and at least one of the noise signal and the magnetic resonance signal as the first input parameter.

[0134] In one embodiment, the computer program, when executed by the processor, further implements the following steps: inputting the first input parameter into a first fault determination model to obtain a fault determination result; the fault determination result comprising whether the magnetic resonance coil has a fault and a receiving channel number of the fault; and determining a second input parameter of a second fault determination model according to the fault determination result, inputting the second input parameter into the second fault determination model to obtain a type of the fault and a level of the fault.

[0135] In one embodiment, the computer program, when executed by the processor, further implements the following steps: if the fault determination result is that the magnetic resonance coil has a fault, determining the second input parameter according to at least one of the noise signal and the magnetic resonance signal corresponding to the receiving channel number of the fault.

[0136] In one embodiment, the type of the fault comprises at least one of a loop disconnection of the magnetic resonance coil, a frequency offset of the magnetic resonance coil, and a receiving chain disconnection of the magnetic resonance coil.

[0137] In one embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the following steps:

[0138] obtaining a magnetic resonance pre-scan signal received by a magnetic resonance coil, the magnetic resonance pre-scan signal comprising a noise signal and a magnetic resonance signal generated after a radio frequency pulse excitation;

[0139] determining a first input parameter of a self-checking model according to at least one of the noise signal and the magnetic resonance signal;

[0140] inputting the first input parameter into the self-checking model to obtain self-checking information of the magnetic resonance coil.

[0141] In one embodiment, the magnetic resonance coil comprises a plurality of receiving channels, and the self-checking information of the magnetic resonance coil comprises at least one of a receiving channel number of the fault, a type of the fault, and a level of the fault.

[0142] In an embodiment, the computer program, when executed by the processor, further implements the following steps: obtaining magnetic resonance coil attribute information, the magnetic resonance coil attribute information comprising at least one of coil size, coil material, coil category, and the number of receiving channels included in the coil; and inputting the magnetic resonance coil attribute information and at least one of the noise signal and the magnetic resonance signal as the first input parameter.

[0143] In an embodiment, the computer program, when executed by the processor, further implements the following steps: inputting the first input parameter into a first fault determination model to obtain a fault determination result; the fault determination result comprising whether the magnetic resonance coil has a fault and the number of the receiving channel that has a fault; determining a second input parameter of a second fault determination model according to the fault determination result, inputting the second input parameter into the second fault determination model to obtain a fault type and a fault level.

[0144] In an embodiment, the computer program, when executed by the processor, further implements the following steps: if the fault determination result is that the magnetic resonance coil has a fault, determining the second input parameter according to at least one of the noise signal and the magnetic resonance signal corresponding to the number of the receiving channel that has a fault.

[0145] In an embodiment, the fault type comprises at least one of a loop disconnection of the magnetic resonance coil, a frequency offset of the magnetic resonance coil, and a receiving chain disconnection of the magnetic resonance coil.

[0146] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0147] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0148] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the patent scope of the present application. It should be noted that for those skilled in the art, without departing from the concept of the present application, some modifications and improvements can be made, which are all within the protection scope of the present application. Therefore, the patent protection scope of the present application should be subject to the appended claims.

Claims

1. A method of self-checking a magnetic resonance coil, characterized by, The method comprises: acquiring a magnetic resonance pre-scan signal received by a magnetic resonance coil, the magnetic resonance pre-scan signal comprising a noise signal and a magnetic resonance signal generated after excitation by a radio frequency pulse; the magnetic resonance coil comprises a plurality of receiving channels; determining a first input parameter of a self-checking model according to at least one of the noise signal and the magnetic resonance signal; the first input parameter is the noise signal and the magnetic resonance signal; inputting the first input parameter into the self-checking model to obtain self-checking information of the magnetic resonance coil; wherein the self-checking model automatically retrieves noise probability distribution data of a corresponding coil noise database, fits a Weibull probability distribution, combines noise distribution data of each receiving channel of the magnetic resonance coil, establishes a two-dimensional probability distribution space, and obtains the self-checking information of the magnetic resonance coil; the self-checking information comprises normal coil channels or faulty coil channels in the magnetic resonance coil.

2. The method of self-testing a magnetic resonance coil of claim 1, wherein, The magnetic resonance coil comprises a plurality of receiving channels, and the self-checking information of the magnetic resonance coil comprises at least one of a number of faulty receiving channels, a type of fault, and a level of fault.

3. The method of self-testing a magnetic resonance coil of claim 1, wherein, The method further comprises: acquiring magnetic resonance coil attribute information, the magnetic resonance coil attribute information comprising at least one of a coil size, a coil material, a coil category, and a number of receiving channels included in the coil; inputting the magnetic resonance coil attribute information and the noise signal and the magnetic resonance signal as the first input parameter.

4. The method of self-testing a magnetic resonance coil of claim 2, wherein, The self-checking model comprises a first fault determination model and a second fault determination model, and the method further comprises: inputting the first input parameter into the first fault determination model to obtain a fault determination result; the fault determination result comprises whether the magnetic resonance coil has a fault and a number of faulty receiving channels; determining a second input parameter of the second fault determination model according to the fault determination result, inputting the second input parameter into the second fault determination model to obtain a type of fault and a level of fault.

5. The method of self-testing a magnetic resonance coil of claim 4, wherein, The method further comprises: if the fault determination result is that the magnetic resonance coil has a fault, determining the second input parameter according to at least one of the noise signal and the magnetic resonance signal corresponding to the number of faulty receiving channels.

6. The method of self-testing a magnetic resonance coil according to claim 2 or 4, characterized in that, The type of fault comprises at least one of: a loop of the magnetic resonance coil being disconnected, a frequency of the magnetic resonance coil being offset, and a receiving chain of the magnetic resonance coil being disconnected.

7. A self-test device for a magnetic resonance coil, characterized by The method comprises: an acquisition module, configured to acquire a magnetic resonance pre-scan signal received by a magnetic resonance coil, the magnetic resonance pre-scan signal comprising a noise signal and a magnetic resonance signal generated after excitation by a radio frequency pulse; the magnetic resonance coil comprises a plurality of receiving channels; a first determination module, configured to determine a first input parameter of a self-checking model according to at least one of the noise signal and the magnetic resonance signal; The first input parameter is the noise signal and the magnetic resonance signal; A second determining module is configured to input the first input parameter into the self-checking model to obtain self-checking information of the magnetic resonance coil; The self-checking model automatically retrieves noise probability distribution data of a corresponding coil noise database, fits a Weibull probability distribution, combines noise distribution data of each receiving channel of the magnetic resonance coil, establishes a two-dimensional probability distribution space, and obtains the self-checking information of the magnetic resonance coil; the self-checking information includes normal coil channels or fault coil channels in the magnetic resonance coil. 8.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-7. The processor executes the computer program to implement the steps of the method of any one of claims 1 to 6.

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

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

Images