Active dynamic shimming method and system

Abstract

The invention relates to the field of medical equipment, in particular to an active dynamic shimming method and system used for a magnetic resonance accelerator, and the magnetic resonance accelerator comprises a radiotherapy system and a magnetic resonance system. The method comprises the following steps: acquiring a dynamic shimming database, link delay time and first position information and first change information of a radiotherapy system at a first moment; based on the dynamic shimming database, the first position information, the first change information and the link delay time, determining a B0 field compensation amount corresponding to the second moment; performing compensation processing on the B0 field corresponding to the second moment based on the B0 field compensation amount corresponding to the second moment to obtain first acquisition data of the magnetic resonance system; and determining a magnetic resonance image corresponding to the second moment based on the first acquisition data. According to the method, the B0 field change caused by the radiotherapy system in the working process can be compensated in real time, the magnetic resonance imaging quality is ensured, and the treatment effect is improved.

Description

Technical Field

[0001] The present specification relates to the field of medical equipment, and in particular to an active dynamic shimming method and system. Background Art

[0002] The magnetic resonance accelerator (MR-Linac) system is a linear accelerator system guided by magnetic resonance. It is used for radiotherapy and has the advantage of being non-invasive and suitable for the treatment of a variety of cancers.

[0003] Magnetic resonance accelerators can use magnetic resonance systems to monitor tumors in real time during radiotherapy, and feed back magnetic resonance image data to radiotherapy equipment to adjust radiotherapy parameters in real time. It can be seen that the effect of magnetic resonance images is closely related to the accuracy of adjusting radiotherapy parameters, so a method is needed to improve the imaging effect of magnetic resonance images in magnetic resonance accelerators. Summary of the invention

[0004] One of the embodiments of the present specification provides an active dynamic shimming method for a magnetic resonance accelerator, wherein the magnetic resonance accelerator includes a radiotherapy system and a magnetic resonance system, and the method includes: acquiring a dynamic shimming database, a link delay time, and first position information and first change information of the radiotherapy system at a first moment; the dynamic shimming database includes the B0 field distribution of the radiotherapy system at multiple positions; based on the dynamic shimming database, the first position information, the first change information, and the link delay time, determining a B0 field compensation amount corresponding to a second moment; based on the B0 field compensation amount corresponding to the second moment, compensating the B0 field corresponding to the second moment to obtain first acquisition data of the magnetic resonance system; based on the first acquisition data, determining a magnetic resonance image corresponding to the second moment.

[0005] In some embodiments, determining the B0 field compensation amount corresponding to the second moment includes: estimating the second position information at the second moment based on the first position information, the first change information and the link delay time; determining the first B0 field distribution corresponding to the first position information and the second B0 field distribution corresponding to the second position information based on the dynamic uniform field database; determining the B0 field compensation amount corresponding to the second moment based on the first B0 field distribution and the second B0 field distribution.

[0006] In some embodiments, the estimated second position information at the second moment includes: the first change information includes movement information of the frame and / or treatment head of the radiotherapy system at the first moment; the movement information includes at least one of angular velocity and acceleration.

[0007] In some embodiments, the method also includes correcting the B0 field compensation amount corresponding to the second moment: at least based on the B0 field compensation amount corresponding to the first moment and the B0 field compensation amount corresponding to the second moment, determining a correction value of the B0 field compensation amount corresponding to the second moment through a correction model.

[0008] In some embodiments, determining the magnetic resonance image corresponding to the second moment based on the first acquisition data includes: determining the magnetic resonance image corresponding to the second moment through post-processing based on the B0 field residual and the first acquisition data; wherein the B0 field residual is determined based on the dynamic shim database, the actual B0 field compensation amount corresponding to the second moment and the first position information at the first moment.

[0009] In some embodiments, the post-processing is performed by a post-processing model, which is a machine learning model; the training process of the post-processing model includes: training the post-processing model together with a quality evaluation model; the quality evaluation model is used to determine whether the input post-processed magnetic resonance image meets the requirements. One of the embodiments of this specification also provides an active dynamic shimming system, which is configured for a magnetic resonance accelerator, the magnetic resonance accelerator includes a radiotherapy system and a magnetic resonance system, the system includes: a data acquisition module, used to acquire a dynamic shimming database, a link delay time, and a first position information and a first change information of the radiotherapy system at a first moment; the dynamic shimming database includes a plurality of B0 field distributions of the radiotherapy system; a compensation determination module, based on the dynamic shimming database, the first position information, the first change information and the link delay time, determines the B0 field compensation amount corresponding to the second moment; a compensation processing module, used to compensate the B0 field corresponding to the second moment based on the B0 field compensation amount corresponding to the second moment, and obtain the first acquisition data of the magnetic resonance system; an image determination module, used to determine the magnetic resonance image corresponding to the second moment based on the first acquisition data.

[0010] One of the embodiments of the present specification provides an active dynamic shimming device, comprising a processor, wherein the processor is used to execute the above-mentioned active dynamic shimming method.

[0011] The active dynamic field shimming method and system provided in this specification can compensate for the B0 field changes caused by the radiotherapy system during operation in real time, ensure the quality of magnetic resonance imaging, and improve the treatment effect; at the same time, the link delay time is taken into account in the compensation process and post-processing is performed to make the compensation result more accurate.

[0012] One of the embodiments of the present specification also provides an active dynamic shimming method for a magnetic resonance accelerator, the magnetic resonance accelerator comprising a radiotherapy system and a magnetic resonance system, the method comprising: acquiring second acquisition data of a scanned object through the magnetic resonance system; acquiring a dynamic shimming database, a link delay time, and first position information and first change information of the radiotherapy system at a first moment; the dynamic shimming database comprising the B0 field distribution of the radiotherapy system at multiple positions; determining a B0 field compensation amount corresponding to a second moment based on the dynamic shimming database, the first position information, the first change information, and the link delay time; and determining a magnetic resonance image corresponding to the second moment through post-processing based on the B0 field compensation amount corresponding to the second moment and the second acquisition data.

[0013] In some embodiments, the post-processing is performed by a post-processing model, which is a machine learning model; the training process of the post-processing model includes: training the post-processing model together with a quality assessment model; the quality assessment model is used to determine whether the input post-processed magnetic resonance image meets the requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0015] Figure 1 is an example diagram of an exemplary medical system according to some embodiments of the present specification;

[0016] Figure 2 is a schematic diagram of an exemplary computing device on which at least a portion of a medical system may be implemented according to some embodiments of the present specification;

[0017] Figure 3 is a schematic diagram of the structure of a magnetic resonance accelerator according to some embodiments of this specification;

[0018] Figure 4 is an exemplary flow chart of an active dynamic shimming method according to some embodiments of this specification;

[0019] Figure 5 is an exemplary flow chart for determining the B0 field compensation amount corresponding to the second moment according to some embodiments of this specification;

[0020] Figure 6 It is a module diagram of an active dynamic shimming system according to some embodiments of this specification. DETAILED DESCRIPTION

[0021] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0022] It should be understood that the "system", "device", "unit" and / or "module" used herein are 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.

[0023] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0024] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0025] Figure 1 is an example diagram of an exemplary medical system according to some embodiments of the present specification.

[0026] The medical system 100 may include a magnetic resonance accelerator 110, a network 120, one or more terminals 130, a processing device 140, and a storage device 150. The components in the medical system 100 may be connected in various ways. By way of example only, the magnetic resonance accelerator 110 may be connected to the processing device 140 directly (as shown by the dotted double-headed arrow connecting the magnetic resonance accelerator 110 and the processing device 140) or through the network 120. As yet another example, the storage device 150 may be connected to the magnetic resonance accelerator 110 directly (as shown by the dotted double-headed arrow connecting the storage device 150 and the magnetic resonance accelerator 110) or through the network 120. As yet another example, the terminal 130 may be connected to the processing device 140 directly (as shown by the dotted double-headed arrow connecting the terminal 130 and the processing device 140) or through the network 120. As yet another example, the terminal 130 may be connected to the storage device 150 directly (as shown by the dotted double-headed arrow connecting the terminal 130 and the storage device 150) or through the network 120.

[0027] The magnetic resonance accelerator 110 can image and / or treat an object. In some embodiments, the object can include a biological object and / or a non-biological object. For example, the object can include a specific part of a human body, such as the head, chest, abdomen, etc., or a combination thereof. For another example, the object can be a patient to be scanned / treated by the magnetic resonance accelerator 110. For more information about the magnetic resonance accelerator 110, see Figure 3 content.

[0028] The network 120 may include any suitable network that can facilitate the exchange of information and / or data of the medical system 100. In some embodiments, one or more components of the medical system 100 (e.g., the magnetic resonance accelerator 110, the terminal 130, the processing device 140, the storage device 150) may communicate information and / or data with one or more other components of the medical system 100 via the network 120. For example, the processing device 140 may obtain scanning data from the magnetic resonance accelerator 110 via the network 120. As another example, the processing device 140 may obtain a user instruction from the terminal 130 via the network 120. The network 120 may be and / or include a public network (e.g., the Internet), a private network (e.g., a local area network (LAN), a wide area network (WAN)), a wired network (e.g., a wireless LAN), Ethernet, a wireless network (e.g., an 802.11 network, a Wi-Fi network), a cellular network (e.g., a Long Term Evolution (LTE) network), a frame relay network, a virtual private network (“VPN”), a satellite network, a telephone network, a router, a hub, a switch, a server computer, and / or any combination thereof. By way of example only, the network 120 may include a cable network, a wired network, a fiber optic network, a telecommunications network, an intranet, a wireless local area network (WLAN), a metropolitan area network (MAN), a public switched telephone network (PSTN), a Bluetooth TM In some embodiments, the network 120 may include a wireless network, a ZigBee network, a near field communication (NFC) network, etc., or any combination thereof. In some embodiments, the network 120 may include one or more network access points. For example, the network 120 may include a wired and / or wireless network access point such as a base station and / or an Internet exchange point, and one or more components of the medical system 100 may be connected to the network 120 through a wired and / or wireless access point to exchange data and / or information.

[0029] The terminal 130 may include a mobile device 130-1, a tablet computer 130-2, a laptop computer 130-3, etc., or any combination thereof. In some embodiments, the mobile device 130-1 may include a smart home device, a wearable device, a smart mobile device, a virtual reality device, an augmented reality device, etc., or any combination thereof. As an example only, the terminal 130 may include a mobile device as shown in the figure. In some embodiments, the smart home device may include a smart lighting device, a smart appliance control device, a smart monitoring device, a smart TV, a smart camera, an intercom, etc., or any combination thereof. In some embodiments, the wearable device may include a bracelet, footwear, glasses, a helmet, a watch, clothing, a backpack, a smart accessory, etc., or any combination thereof. In some embodiments, the mobile device may include a mobile phone, a personal digital assistant (PDA), a gaming device, a navigation device, a point of sale (POS) device, a laptop computer, a tablet computer, a desktop computer, etc., or any combination thereof. In some embodiments, the virtual reality device and / or the augmented reality device may include a virtual reality helmet, virtual reality glasses, virtual reality goggles, augmented reality helmets, augmented reality glasses, augmented reality goggles, etc., or any combination thereof. For example, the virtual reality device and / or the augmented reality device may include Google Glass TM 、Oculus Rift TM 、Hololens TM 、Gear VR TM Etc. In some embodiments, one or more terminals 130 may be part of a processing device 140 .

[0030] The processing device 140 may process data and / or information obtained from the magnetic resonance accelerator 110, the terminal 130, and / or the storage device 150. For example, the processing device 140 may acquire one or more sets of acquisition data of the object. As another example, the processing device 140 may determine a magnetic resonance image based on the acquisition data. In some embodiments, the processing device 140 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processing device 140 may be a local component or a remote component relative to one or more other components of the medical system 100. For example, the processing device 140 may access information and / or data stored in the magnetic resonance accelerator 110, the terminal 130, and / or the storage device 150 via the network 120. As another example, the processing device 140 may be directly connected to the magnetic resonance accelerator 110, the terminal 130, and / or the storage device 150 to access the stored information and / or data. In some embodiments, the processing device 140 may be implemented on a cloud platform. By way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-layer cloud, etc., or any combination thereof. In some embodiments, the processing device 140 may be provided by a processor having a plurality of processors such as a processor 100 and a processor 101. Figure 2 The computing device 200 may be implemented with one or more of the components shown.

[0031] When applied to a medical system, the processing device 140 can obtain acquisition data or image data from the medical device via a transmission device. For example, the processing device 140 can obtain user instructions via a transmission device. For another example, the processing device 140 can send treatment queues, patient information, etc. to a host computer via a transmission device to display to the user. For another example, the processing device 140 may include a first processor and a second processor. The first processor can send data such as treatment queues and patient information to the host computer via Ethernet using the TCP / IP protocol, and the second processor can send information such as mechanical parameters and hardware status of components of the medical device to the host computer via Ethernet using the TCP / IP protocol. The application running on the host computer can present these data to the user.

[0032] The storage device 150 may store data, instructions, and / or any other information. In some embodiments, the storage device 150 may store data obtained from the terminal 130 and / or the processing device 140. In some embodiments, the storage device 150 may store data and / or instructions that the processing device 140 may execute or use to execute the exemplary methods described in this specification. In some embodiments, the storage device 150 may include a mass storage, a removable memory, a volatile read-write memory, a read-only memory (ROM), etc., or any combination thereof. Exemplary mass storage may include a disk, an optical disk, a solid-state drive, etc. Exemplary removable memory may include a flash drive, a floppy disk, an optical disk, a memory card, a compressed disk, a tape, etc. Exemplary volatile read-write memory may include a random access memory (RAM). Exemplary RAM may include a dynamic random access memory (DRAM), a double data rate synchronous dynamic random access memory (DDR SDRAM), a static random access memory (SRAM), a thyristor random access memory (T-RAM), and a zero capacitance random access memory (Z-RAM), etc. Exemplary ROMs may include mask ROM (MROM), programmable ROM (PROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), compact disk ROM (CD-ROM), and digital versatile disk ROM, etc. In some embodiments, the storage device 150 may be implemented on a cloud platform. By way of example only, a cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-layer cloud, etc., or any combination thereof.

[0033] In some embodiments, the storage device 150 can be connected to the network 120 to communicate with one or more other components of the medical system 100 (e.g., the processing device 140, the terminal 130). One or more components of the medical system 100 can access data or instructions stored in the storage device 150 via the network 120. In some embodiments, the storage device 150 can be directly connected to or communicate with one or more other components of the medical system 100 (e.g., the processing device 140, the terminal 130). In some embodiments, the storage device 150 can be part of the processing device 140.

[0034] In some embodiments, a coordinate system 170 may be provided for the magnetic resonance accelerator 110 to define the position (e.g., absolute position, position relative to another component) and / or the movement of a component of the magnetic resonance accelerator 110. For example, the coordinate system 170 may include an X-axis, a Y-axis, and a Z-axis. The X-axis and the Y-axis are axes in the horizontal direction, and the Z-axis is an axis in the vertical direction. Figure 1 As shown, the positive direction of the X-axis may be the direction from the left side of the treatment bed to the right side when looking toward the front of the magnetic resonance accelerator 110; the positive direction of the Y-axis may be the direction in which the treatment bed moves from the inside to the outside of the magnetic resonance accelerator 110; the positive direction of the Z-axis may be the direction from the bottom of the magnetic resonance accelerator 110 (or the ground where the magnetic resonance accelerator 110 is located) to the top of the magnetic resonance accelerator 110. The coordinate system 170 is provided only for the purpose of illustration, for example, the coordinate system 170 may also include other coordinate axes. For another example, the directions of the X-axis, the Y-axis, and the Z-axis may be other directions, which are not limited in this specification.

[0035] It should be noted that the above description is provided for illustrative purposes only and is not intended to limit the scope of this specification. For those of ordinary skill in the art, under the guidance of the contents of this specification, various changes and modifications can be made. The features, structures, methods and other features of the exemplary embodiments described in this specification can be combined in various ways to obtain additional and / or alternative exemplary embodiments. However, these changes and modifications will not deviate from the scope of this specification.

[0036] Figure 2 is a schematic diagram of an exemplary computing device on which at least a portion of a medical system may be implemented according to some embodiments of the present description.

[0037] like Figure 2 As shown, computing device 200 may include processor 210 , memory 220 , input / output (I / O) 230 , and communication port 240 .

[0038] The processor 210 can execute computer instructions (e.g., program code) and perform the functions of the processing device 140 according to the techniques described in this specification. The computer instructions may include, for example, routines, programs, objects, components, data structures, processes, modules, and functions, which perform specific functions described in this specification. For example, the processor 210 can process data or information obtained from the magnetic resonance accelerator 110, the storage device 150, the terminal 130, and / or any other component of the medical system 100. In some embodiments, the processor 210 may include one or more hardware processors, such as a microcontroller, a microprocessor, a reduced instruction set computer (RISC), an application specific integrated circuit (ASIC), an application specific instruction set processor (ASIP), a central processing unit (CPU), a graphics processing unit (GPU), a physical processing unit (PPU), a microcontroller unit, a digital signal processor (DSP), a field programmable gate array (FPGA), an advanced RISC machine (ARM), a programmable logic device (PLD), any circuit or processor capable of performing one or more functions, etc., or a combination thereof.

[0039] For illustration purposes only, only one processor is described in the computing device 200. However, it should be noted that the computing device 200 disclosed in this specification may also include multiple processors. Therefore, the operations and / or method steps disclosed in this specification that are performed by one processor may also be performed jointly or separately by multiple processors. For example, if in this specification, the processor of the computing device 200 performs operation A and operation B, it should be understood that operation A and operation B may also be performed jointly or separately by two or more different processors in the computing device 200 (for example, the first processor performs operation A, the second processor performs operation B, or the first processor and the second processor perform operations A and B together).

[0040] The memory 220 may store data / information obtained from the magnetic resonance accelerator 110, the storage device 150, the terminal 130, and / or any other component of the medical system 100. In some embodiments, the memory 220 may include a mass storage, a removable storage, a volatile read-write storage, a read-only storage, or the like, or any combination thereof. For example, the mass storage may include a magnetic disk, an optical disk, a solid-state drive, or the like. The removable storage may include a flash drive, a floppy disk, an optical disk, a memory card, a compressed disk, a magnetic tape, or the like. The volatile read-write storage may include a random access memory (RAM). The RAM may include a dynamic RAM (DRAM), a double data rate synchronous dynamic RAM (DDR SDRAM), a static RAM (SRAM), a thyristor RAM (T-RAM), and a zero capacitor RAM (Z-RAM), or the like. The ROM may include a mask ROM (MROM), a programmable ROM (PROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a compact disk ROM (CD-ROM), and a digital versatile disk ROM, or the like. In some embodiments, the memory 220 may store one or more programs and / or instructions to execute the exemplary methods described in this specification.

[0041] Input / output 230 may input and / or output signals, data, information, etc. In some embodiments, input / output 230 may enable a user to interact with processing device 140. In some embodiments, input / output 230 may include input devices and output devices. Exemplary input devices may include a keyboard, a mouse, a touch screen, a microphone, etc., or a combination thereof. Exemplary output devices may include a display device, a speaker, a printer, a projector, etc., or a combination thereof. Exemplary display devices may include a liquid crystal display (LCD), a light emitting diode (LED) based display, a flat panel display, a curved screen, a television device, a cathode ray tube (CRT), a touch screen screen, etc., or a combination thereof.

[0042] The communication port 240 can be connected to a network (e.g., network 120) to facilitate data communication. The communication port 240 can establish a connection between the processing device 140 and the magnetic resonance accelerator 110, the storage device 150, and / or the terminal 130. The connection can be a wired connection, a wireless connection, any other communication connection that can realize data transmission and / or reception, and / or a combination of these connections. The wired connection may include, for example, an electric cable, an optical cable, a telephone line, etc., or any combination thereof. The wireless connection may include, for example, Bluetooth, Wi-Fi, WiMax, a wireless LAN, ZigBee, a mobile network (e.g., 3G, 4G, 5G), etc., or a combination thereof. In some embodiments, the communication port 240 may be and / or include a standardized communication port, for example, RS232, RS485, etc. In some embodiments, the communication port 240 may be a specially designed communication port. For example, the communication port 240 may be designed according to the Digital Imaging and Communications in Medicine (DICOM) protocol.

[0043] In some embodiments, the memory 220 in the computing device 200 may store a computer program, and the processor 210 may execute the computer program to implement an active dynamic shimming method for a magnetic resonance accelerator.

[0044] Figure 3 It is a schematic diagram of the structure of a magnetic resonance accelerator according to some embodiments of this specification.

[0045] As shown in the figure, the magnetic resonance accelerator 300 may include a radiotherapy (RT) system 310 near the outside and a magnetic resonance (MR) system 320 near the inside, which is used to guide radiotherapy using magnetic resonance images. Specifically, the magnetic resonance system 320 can monitor the area to be treated in real time before and during radiotherapy, and can also feed back the position and shape of the object (such as a tumor) in the area to be treated to the radiotherapy system 310 in real time. The radiotherapy system 310 adjusts the treatment parameters in real time according to the image information fed back by the magnetic resonance system 320 to reduce damage to normal tissues.

[0046] In some embodiments, the radiotherapy system 310 may further include a gantry 312 and a treatment head 314. The gantry 312 is configured to be able to Figure 1 The treatment head 314 is relatively fixed to the frame 312 and can rotate along the circumference of the frame 312 driven by the frame 312, and the treatment head 314 itself can rotate along the central axis. At different rotation angles of the treatment head 314 and the frame 312, radiotherapy of the object can be achieved and the accuracy of positioning the target area can be improved to achieve better treatment effects.

[0047] Since the magnetic resonance imaging process requires the application of a magnetic field of a certain strength, the components of the radiotherapy system 310 in the magnetic resonance accelerator 300 (such as the gantry 312 and / or the treatment head 314) may be weakly magnetic materials, which will affect the data collected by the magnetic resonance system 320 (such as B0 field data), thereby having a negative impact on the accuracy and effect of the magnetic resonance imaging, and further affecting the treatment effect.

[0048] In some embodiments, the magnetic field generated by the radiotherapy system 310 can be obtained and offset in the process of generating magnetic resonance images. However, during the treatment of the magnetic resonance accelerator 300, the radiotherapy system 310 is dynamic, so this method cannot improve the imaging effect of the magnetic resonance image very well. In view of this, some embodiments of the present specification provide an active dynamic field shim method to actively and continuously compensate for the B0 field.

[0049] Figure 4 is an exemplary flow chart of an active dynamic shimming method according to some embodiments of the present specification.

[0050] Figure 5 This is an exemplary flow chart for determining the B0 field compensation amount corresponding to the second moment according to some embodiments of this specification.

[0051] Figure 4 As shown, one or more steps in the process 400 of the active dynamic shimming method can be performed by Figure 2 In some embodiments, the process 400 may include:

[0052] Step 410 , acquiring a dynamic shimming database, a link delay time, and first position information and first change information of a radiotherapy system at a first moment. In some embodiments, step 410 may be performed by a data acquisition module 610 .

[0053] In some embodiments, when the magnetic resonance accelerator is running, the B0 field distribution of the radiotherapy system at multiple positions can be collected and a dynamic shimming database can be obtained. The B0 field distribution can reflect the influence of the gantry and treatment head of the radiotherapy system on the B0 field when they are respectively at multiple positions (such as various angles). The collected data of the magnetic resonance system can be processed through the B0 field distribution to offset the influence of the magnetic field generated by the radiotherapy system on the magnetic resonance image and realize the "shimming" of the magnetic field inside the magnetic resonance accelerator. In some embodiments, each combination of the position of the gantry and the treatment head (such as {gantry 30°, treatment head 45°}, {gantry 90°, treatment head 40°}, etc.) can correspond to a three-dimensional B0 field matrix and be stored in the dynamic shimming database. The three dimensions of the matrix respectively represent the treatment space (such as Figure 1 The X-axis, Y-axis and Z-axis of the coordinate system 170), the elements of the matrix represent the B0 field magnetic field strength at that position.

[0054] In some embodiments, since the gantry and treatment head of the radiotherapy system may move during the magnetic resonance accelerator treatment process, the collected data of the magnetic resonance system can be processed in time according to the movement of the gantry and treatment head to achieve dynamic field shimming.

[0055] Therefore, before actually using the magnetic resonance accelerator for treatment, a calibration phase for the magnetic resonance accelerator can be added. In the calibration phase, the B0 field distribution generated when the gantry and treatment head of the radiotherapy system are at various angles can be acquired and recorded through the acquisition device to construct a dynamic shimming database. When the magnetic resonance accelerator is used for treatment, the angles of the gantry and treatment head of the radiotherapy system are acquired at any time, and the corresponding influence information on the B0 field can be obtained by querying the dynamic shimming database, so that the acquired data of the magnetic resonance system can be processed.

[0056] In some embodiments, during the calibration phase, the angles of different racks and treatment heads may be discrete values, such as increasing in steps of 1°, 5°, 10°, etc. The step size may be determined based on the actual accuracy required.

[0057] Taking a step length of 10° as an example, since the working angles of the gantry and treatment head of the radiotherapy system are both 0 to 360°, it is necessary to obtain the B0 field distribution of the gantry and treatment head at 36 positions respectively. It should be noted that since the B0 field distribution of the gantry and treatment head at different positions is not linearly superimposed, during the calibration phase, for each gantry angle (such as when the gantry is 10°), it is necessary to obtain the B0 field distribution of the treatment head at 36 positions; the same is true for the treatment head. It can be seen that at this time, 36*36 groups, that is, 1296 groups of B0 field distributions need to be collected to obtain a dynamic uniform field database.

[0058] The link delay time may include at least one of the time required for querying the B0 field distribution in the dynamic shimming database, the time required for transmitting the queried B0 field distribution data, and the time required for the magnetic resonance system to process the data. Since the time required for data query, transmission, and calculation is usually relatively stable, in some embodiments, the link delay time can be regarded as an inherent property of the magnetic resonance accelerator and can be a fixed value manually determined and preset.

[0059] Due to the existence of link delay, when the B0 field distribution is queried based on the initial position of the radiotherapy system and after transmission and calculation, the radiotherapy system may actually move to a new position, that is, the angle of the treatment head and / or the rack may change, and at this time the influence of the radiotherapy system on the B0 field also changes. Therefore, the initial position is used as the first position information at the first moment, and the moment after the link delay time of the first moment is used as the second moment. In some embodiments, the first position information can be a three-dimensional coordinate.

[0060] The first change information may represent movement information of a gantry or treatment head in the radiotherapy system, such as speed, acceleration, etc. In some embodiments, the position of a gantry or treatment head in the radiotherapy system may be predicted based on the first change information at the first moment and the link delay time.

[0061] Step 420 , based on the dynamic shimming database, the first position information, the first change information and the link delay time, determine the B0 field compensation amount corresponding to the second moment. In some embodiments, step 420 may be performed by the compensation determination module 620 .

[0062] In some embodiments, the B0 field compensation amount corresponding to the second moment is used to compensate the acquisition data of the magnetic resonance system at the second moment (i.e., the B0 field) to reduce the interference of the radiotherapy system on the acquisition data of the magnetic resonance system and improve the quality of the magnetic resonance image. The B0 field compensation amount can be a matrix of the same dimension as the B0 field (i.e., a three-dimensional matrix), and each element in the matrix of the B0 field compensation amount is the value that needs to be compensated for the element at the corresponding position of the B0 field matrix.

[0063] In some embodiments, the process of determining the B0 field compensation amount corresponding to the second moment may further include:

[0064] Step 510: Estimate second location information at a second moment based on the first location information, the first change information, and the link delay time.

[0065] In some embodiments, the first change information may include movement information of the frame and / or the treatment head at the first moment, and the movement information may include the angular velocity ω 0 and the acceleration α at the first moment 0 , the first position information at the first moment is represented as θ 0 , the link delay time is represented as T, then based on the speed and acceleration formula, the second position information at the second moment is estimated. In some embodiments, the second position information θ at the second moment can be expressed as:

[0066] In some embodiments, the motion information may also include acceleration (third-order derivative of displacement) or higher-order data, and the second position information θ may further increase the displacement change caused by the acceleration formula, taking into account the multi-order first change information, to obtain more accurate second position information. Therefore, based on the first position information, the first change information and the link delay time, the second position information may be estimated by Taylor expansion. In some embodiments, the Taylor expansion may be in the form of formula (1) with the acceleration calculation formula added, or a higher-order term.

[0067] Step 520: Determine a first B0 field distribution corresponding to the first position information and a second B0 field distribution corresponding to the second position information based on the dynamic shimming database.

[0068] The second B0 field distribution corresponding to the second position information may be obtained by querying the second position information θ in the dynamic shimming database.

[0069] Step 530: Determine a B0 field compensation amount corresponding to a second moment based on the first B0 field distribution and the second B0 field distribution.

[0070] In some embodiments, the B0 field compensation amount corresponding to the second moment may be the difference between the first B0 field distribution and the second B0 field distribution. Specifically, the B0 field compensation amount corresponding to the second moment may be calculated by matrix subtraction of the first B0 field distribution matrix and the second B0 field distribution matrix.

[0071] Since it is necessary to continuously obtain the B0 field compensation amount corresponding to each time interval during the treatment process, such as obtaining the first B0 field compensation amount from time t0 to time t1, and obtaining the second B0 field compensation amount from time t1 to time t2, it can be seen that the B0 field compensation amount is continuously and dynamically obtained, and the latter B0 field compensation amount is affected by the previous B0 field compensation amount. Therefore, in some embodiments, in the process of determining the B0 field compensation amount corresponding to the second moment, the B0 field compensation amount can also be corrected. Specifically, the correction value of the B0 field compensation amount corresponding to the second moment can be determined by correcting the model based on at least the B0 field compensation amount corresponding to the first moment and the B0 field compensation amount corresponding to the second moment. The B0 field compensation amount obtained in step 520 is superimposed with the correction value of the B0 field compensation amount to determine a more accurate B0 field compensation amount.

[0072] In some embodiments, the correction model can be obtained through training using training data. Optionally, the correction model can be a data fitting algorithm model or a machine learning model (such as a neural network model). Taking the machine learning algorithm as an example, the training samples of the model may include multiple groups of B0 field compensation data at consecutive moments, and the training labels are theoretical B0 field compensation values ​​at multiple times. The labels can be determined based on the quality of the magnetic resonance image (for example, the doctor can select the actual magnetic resonance image with the highest quality and use the B0 field compensation value corresponding to the image as the label). In actual prediction, the B0 field compensation amount at the first moment (i.e., the B0 field compensation amount at the previous moment), the B0 field compensation amount at the second moment, the number of estimated items, the step size of the discrete angle in the calibration phase, the equipment model of the radiotherapy system, and the equipment model of the magnetic resonance system, one or more of which can be input into the correction model to obtain the correction value of the B0 field compensation amount. Among them, the number of estimated items is the number of items used in the estimation in formula (1) or Taylor expansion. For example, only the first two items (i.e., θ 0 +ω 0 T) is used for estimation, the number of estimated items is 2. The input of the model is related to the characteristics of the data used in the model training process, which will not be described here.

[0073] Step 430 , based on the B0 field compensation amount corresponding to the second moment, the B0 field corresponding to the second moment is compensated to obtain first acquisition data of the magnetic resonance system. In some embodiments, step 430 may be performed by the compensation processing module 630 .

[0074] The first acquisition data is data collected by the magnetic resonance system when the magnetic resonance accelerator is working, and is used to generate a magnetic resonance image. In some embodiments, it may include, for example, T1 signals and T2 signals. Compensating the B0 field corresponding to the second moment based on the B0 field compensation amount corresponding to the second moment may include superimposing the B0 field data in the acquisition data of the magnetic resonance system at the second moment with the B0 field compensation amount, that is, adding the B0 field compensation amount to the B0 field data in a positional manner, so that the B0 field data in the acquisition data of the magnetic resonance system excludes interference generated by the radiotherapy system, is more accurate, and is close to the objective value.

[0075] Step 440 , based on the first acquisition data, determine the magnetic resonance image corresponding to the second moment. In some embodiments, step 440 may be performed by the image determination module 640 .

[0076] In some embodiments, the magnetic resonance system may generate a magnetic resonance image corresponding to the second moment based on the first acquired data according to its image generation process or algorithm. After compensating the acquired data through the aforementioned steps, the acquired data obtained by the magnetic resonance system is closer to the objective value, and thus a magnetic resonance image with less interference and higher quality can be obtained. In some embodiments, the use of higher quality magnetic resonance images can further assist the radiotherapy process.

[0077] In some embodiments, in order to further reduce the influence of the magnetic field on the magnetic resonance image in order to obtain a magnetic resonance image with better imaging effect in step 440, in some embodiments, step 440 may also include: determining the magnetic resonance image corresponding to the second moment through post-processing based on the B0 field residual and the first acquisition data.

[0078] Considering that the data collected by the magnetic resonance system may include the influence of the B0 field residual in addition to the aforementioned B0 field compensation, therefore, considering removing the influence of the B0 field residual through post-processing, the accuracy of the post-processed magnetic resonance image is further improved, and it can be used for scenes such as real-time guidance of the radiotherapy process. In some embodiments, the B0 field residual includes the value between the B0 field collected by the magnetic resonance system and the B0 field objective value, which may be caused by various factors such as system measurement errors, models of radiotherapy systems and magnetic resonance systems, and other noise interference, except for the B0 field compensation. Similar to the B0 field compensation, the B0 field residual can also be a three-dimensional matrix.

[0079] Specifically, the B0 field residual amount may be determined based on the dynamic shimming database, the B0 field compensation amount corresponding to the second moment, and the first position information at the first moment.

[0080] In some embodiments, as described above, the quality of the magnetic resonance image during the post-processing process is affected by multiple factors within the system, and it is not convenient to directly measure all factors during the actual treatment process. In some embodiments, post-processing can be performed by a post-processing model, that is, the B0 field residual and the first acquisition data can be input into the post-processing model, and the post-processing model outputs the magnetic resonance image corresponding to the second moment. The post-processing model is a machine learning model (such as a neural network model).

[0081] The post-processing model can be obtained by training the initial model through training samples. In some embodiments, the training process of the post-processing model can include training with the quality assessment model. In some embodiments, the post-processing model and the quality assessment model can be trained and parameter adjusted with a structure similar to a generative adversarial network (GAN), that is, the quality assessment model is used to determine whether the input post-processed magnetic resonance image meets the requirements, and the determination result is sent to the post-processing model to adjust the post-processing model parameters.

[0082] Specifically, the training samples of the quality evaluation model are corrected magnetic resonance images, and the label is whether the magnetic resonance image meets the requirements (for example, the magnetic resonance image is evaluated by a physician, and the corresponding label is "1" if it meets the requirements, and the corresponding label is "0" if it does not meet the requirements). The trained quality evaluation model is obtained through supervised training and used as a discriminator; the post-processing model serves as a generator, and its input includes B0 field residual and magnetic resonance acquisition data, and its output is a corrected magnetic resonance image.

[0083] In the training stage, the quality evaluation model is first trained to obtain a trained quality evaluation model, and then the post-processing model is trained, that is, the corrected magnetic resonance image output by the post-processing model is input into the trained quality evaluation model for judgment, and the judgment result is fed back to the post-processing model to adjust the parameters of the post-processing model. In some embodiments, the judgment result of the quality evaluation model can be a value between 0 and 1. After multiple rounds of parameter adjustment, when the judgment result obtained by inputting the image output by the post-processing model into the trained quality evaluation model is greater than a certain threshold (such as 0.9), the training of the post-processing model is completed to obtain a trained post-processing model.

[0084] In some embodiments, the processor may directly process the second acquisition data of the scanned object acquired by the magnetic resonance system through post-processing to determine the magnetic resonance image corresponding to the second moment. The second acquisition data of the scanned object is data of the scanned object directly acquired by the magnetic resonance system in an environment without B0 field compensation processing.

[0085] In some embodiments, the magnetic resonance image corresponding to the second moment can be determined by post-processing based on the B0 field compensation amount corresponding to the second moment and the second acquisition data. Among them, the B0 field compensation amount corresponding to the second moment is similar to the aforementioned process, and can refer to steps 410 and 420 in the above text, which will not be repeated here. Post-processing can also be performed by a post-processing model, and the post-processing model is a machine learning model. In some embodiments, the B0 field compensation amount corresponding to the second moment, the B0 field residual amount, and the second acquisition data can be input into the post-processing model, and the post-processing model outputs the magnetic resonance image corresponding to the second moment.

[0086] Similar to the post-processing model training process in the previous text, the training process of the post-processing model can include joint training with the quality assessment model. In some embodiments, the post-processing model and the quality assessment model can be trained and parameter adjusted with a structure similar to a generative adversarial network (GAN), that is, the quality assessment model is used to determine whether the input post-processed magnetic resonance image meets the requirements, and the judgment result is sent to the post-processing model to adjust the post-processing model parameters. Since the input of the post-processing model is different, the difference from the training of the aforementioned post-processing model is that the post-processing model is used as a generator, and its input includes B0 field compensation, B0 field residual and magnetic resonance acquisition data, and the output is a corrected magnetic resonance image.

[0087] Figure 6 It is a module diagram of an active dynamic shimming system according to some embodiments of this specification.

[0088] like Figure 6 As shown, the active dynamic shimming system 600 may include a data acquisition module 610 , a compensation determination module 620 , a compensation processing module 630 and an image determination module 640 .

[0089] The data acquisition module 610 may be used to acquire a dynamic shimming database, a link delay time, and first position information and first change information of the radiotherapy system at a first moment.

[0090] In some embodiments, more descriptions about the dynamic shimming database, link delay time, first position information, and first change information can be found in the relevant contents of step 410, which will not be repeated here.

[0091] The compensation determination module 620 may determine the B0 field compensation amount corresponding to the second moment based on the dynamic shimming database, the first position information, the first change information, and the link delay time.

[0092] In some embodiments, more descriptions about the B0 field compensation amount corresponding to the second moment can be found in the relevant content of step 420, which will not be repeated here.

[0093] The compensation processing module 630 may be configured to perform compensation processing on the B0 field based on the B0 field compensation amount corresponding to the second moment, to obtain first acquisition data of the magnetic resonance system.

[0094] In some embodiments, more descriptions about the compensation process can be found in the relevant content of step 430, which will not be repeated here.

[0095] The image determination module 640 may be configured to determine the magnetic resonance image corresponding to the second moment based on the first acquisition data.

[0096] In some embodiments, more descriptions about the magnetic resonance image can be found in the relevant content of step 440, which will not be repeated here.

[0097] It should be understood that Figure 6 The system 600 and its modules shown can be implemented in various ways. It should be noted that the above description of the system 600 and its modules is only for the convenience of description and cannot limit the present specification to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the modules or form a subsystem to connect with other modules without deviating from this principle. For example, in some embodiments, for example, Figure 6 The compensation determination module 620 and the compensation processing module 630 disclosed in the specification can be different modules in a system, or a module can realize the functions of two or more modules mentioned above. For another example, each module can share a storage module, or each module can have its own storage module. Such variations are all within the protection scope of this specification.

[0098] The beneficial effects that may be brought about by the embodiments of this specification include but are not limited to: (1) the B0 field changes caused by the radiotherapy system during operation can be compensated in real time to ensure the quality of magnetic resonance imaging and improve the treatment effect; (2) the compensation process takes into account the link delay time, making the compensation result more accurate; (3) by post-processing the data collected by the magnetic resonance system, the imaging effect and accuracy are further improved.

[0099] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or any other beneficial effects that may be obtained.

[0100] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0101] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0102] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0103] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0104] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate 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 change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0105] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. An active dynamic shimming method for a magnetic resonance accelerator, wherein the magnetic resonance accelerator comprises a radiotherapy system and a magnetic resonance system, the method comprising: Acquire a dynamic shimming database, a link delay time, and first position information and first change information of the radiotherapy system at a first moment; The dynamic shimming database includes B0 field distributions at multiple positions of the radiotherapy system; Determine a B0 field compensation amount corresponding to a second moment based on the dynamic shimming database, the first position information, the first change information, and the link delay time; performing compensation processing on the B0 field corresponding to the second moment based on the B0 field compensation amount corresponding to the second moment, so that the magnetic resonance system acquires first acquisition data of the scanned object; A magnetic resonance image corresponding to the second moment is determined based on the first acquisition data.

2. The method of claim 1, wherein: The determining of the B0 field compensation amount corresponding to the second moment includes: estimating second location information at the second moment based on the first location information, the first change information, and the link delay time; Determine, based on the dynamic shimming database, a first B0 field distribution corresponding to the first position information and a second B0 field distribution corresponding to the second position information; A B0 field compensation amount corresponding to the second moment is determined based on the first B0 field distribution and the second B0 field distribution.

3. The method of claim 2, wherein: The estimating the second position information at the second moment includes: The first change information includes movement information of the frame and / or the treatment head of the radiotherapy system at the first moment; the movement information includes at least one of an angular velocity and an angular acceleration.

4. The method according to claim 1, further comprising: correcting the B0 field compensation amount corresponding to the second moment: Based at least on the B0 field compensation amount corresponding to the first moment and the B0 field compensation amount corresponding to the second moment, a correction value of the B0 field compensation amount corresponding to the second moment is determined by correcting the model.

5. The method according to any one of claims 1 to 4, wherein: Determining a magnetic resonance image corresponding to the second moment based on the first acquisition data includes: Based on the B0 field residual and the first acquisition data, the magnetic resonance image corresponding to the second moment is determined through post-processing; wherein the B0 field residual is determined based on the dynamic shim database, the B0 field compensation amount corresponding to the second moment and the first position information at the first moment.

6. The method of claim 5, wherein the post-processing is performed by a post-processing model, and the post-processing model is a machine learning model; The training process of the post-processing model includes: The post-processing model and the quality evaluation model are trained together; the quality evaluation model is used to determine whether the input post-processed magnetic resonance image meets the requirements.

7. An active dynamic shimming system, configured to be used in a magnetic resonance accelerator, the magnetic resonance accelerator comprising a radiotherapy system and a magnetic resonance system, the system comprising: A data acquisition module, used for acquiring a dynamic shimming database, a link delay time, and first position information and first change information of the radiotherapy system at a first moment; The dynamic shimming database includes the B0 field distribution of the radiotherapy system at multiple positions; a compensation determination module, which determines a B0 field compensation amount corresponding to a second moment based on the dynamic shimming database, the first position information, the first change information and the link delay time; a compensation processing module, configured to perform compensation processing on the B0 field corresponding to the second moment based on the B0 field compensation amount corresponding to the second moment, so as to obtain first acquisition data of the magnetic resonance system; An image determination module is used to determine the magnetic resonance image corresponding to the second moment based on the first acquisition data.

8. An active dynamic shimming device, comprising a processor, wherein: The processor is used to execute the active dynamic shimming method according to any one of claims 1 to 6.

9. An active dynamic shimming method for a magnetic resonance accelerator, wherein the magnetic resonance accelerator comprises a radiotherapy system and a magnetic resonance system, the method comprising: Acquiring second acquisition data of the scanned object through the magnetic resonance system; Acquire a dynamic shimming database, a link delay time, and first position information and first change information of the radiotherapy system at a first moment; The dynamic shimming database includes B0 field distributions at multiple positions of the radiotherapy system; Determine a B0 field compensation amount corresponding to a second moment based on the dynamic shimming database, the first position information, the first change information, and the link delay time; Based on the B0 field compensation amount corresponding to the second moment and the second acquisition data, a magnetic resonance image corresponding to the second moment is determined through post-processing.

10. The method of claim 9, wherein the post-processing is performed by a post-processing model, and the post-processing model is a machine learning model; The training process of the post-processing model includes: The post-processing model and the quality evaluation model are trained together; the quality evaluation model is used to determine whether the input post-processed magnetic resonance image meets the requirements.

Images