Motion tracking in magnetic resonance imaging using radar and motion detection systems

Abstract

The present invention provides a medical instrument (100, 300, 400, 500) comprising a magnetic resonance imaging system (102). The medical instrument further comprises an object support (120) having a support surface (121), the support surface being configured to support at least a portion of the object within an imaging region (108). The object support comprises a radar array (125) embedded below the support surface. The medical instrument further comprises a radar system (124) for acquiring radar signals (144) from the object. The medical instrument further comprises a motion detection system (122) configured to acquire movement signals (146). Execution of the machine executable instructions (140) causes the processor (130) to: continuously (200) receive the radar signal; continuously (202) receive the motion signal; continuously (204) calculate a combined motion signal (148) based on the radar signal and the motion signal; and control (206) the magnetic resonance imaging system using pulse sequence commands to acquire the magnetic resonance imaging data, wherein the acquisition of the magnetic resonance imaging data is controlled using the combined motion signal.

Description

Technical Field

[0001] The present invention relates to magnetic resonance imaging and, in particular, to the control of magnetic resonance imaging using radar. Background Art

[0002] Magnetic resonance imaging (MRI) scanners use large static magnetic fields to align the nuclear spins of atoms as part of the process used to produce images of a patient's body. Various quantities or properties of an object can be measured spatially using MRI. However, the acquisition of magnetic resonance imaging data is not instantaneous. During data acquisition, the object may move, which can corrupt the acquisition. Various methods exist for compensating for the motion of the object, including methods for gating the data acquisition.

[0003] U.S. Patent Publication US2005 / 0128123 A1 discloses a system and method for suppressing motion artifacts introduced by movement of a radar detection system. Briefly, in the architecture, one embodiment of the system can be implemented as follows. The system includes a Doppler radar module, which is configured to transmit a microwave signal aimed at a target and receive microwave signals reflected from the target and a living object located behind the target. Moreover, the system includes a reference module, which is configured to transmit a reference signal toward the target and receive a reference signal reflected from the target. By comparing the two reflected signals from the Doppler radar module and the reference device, the signal processor suppresses the motion artifacts generated by the movement of the Doppler radar module to identify the presence of a living object behind the target. Other systems and methods are also provided.

[0004] U.S. Patent Application Publication US2010 / 0271615 A1 discloses a system that uses range and Doppler velocity measurements from a laser radar system and images from a video system to estimate a six-degree-of-freedom trajectory of a target. The system estimates the trajectory in two stages (i.e., a first stage and a second stage): in the first stage, the first stage motion aspects of the target (i.e., the trajectory of the target) are estimated using the range and Doppler velocity measurements from the laser radar system and various feature measurements obtained from the images from the video system; in the second stage, the second stage motion aspects of the target are estimated using the images from the video system and the first stage motion aspects of the target. Once the second stage motion aspects of the target are estimated, a three-dimensional image of the target can be generated.

[0005] US patent application US2014 / 0073908 discloses an MRI system with a motion sensor unit for detecting movement of a patient. Known motion sensor units may be integrated in an RF receiver coil. Summary of the invention

[0006] The invention provides a medical apparatus, a computer program product and a method in the independent claims. Embodiments are given in the dependent claims.

[0007] Radar systems such as ultra-wideband radars have been used to measure the motion of objects for magnetic resonance imaging. However, the radar signal used to guide or trigger the magnetic resonance imaging may be corrupted or contain noise. Embodiments can improve this by using an additional motion detection system to simultaneously measure the mobile signal (which can be combined and / or correlated with the radar signal). For example, data from a camera and / or an ultrasound imaging system (e.g., a Doppler ultrasound imaging system) can be used. This can result in a more robust combined motion signal that can be used for things such as triggering and controlling the acquisition of magnetic resonance imaging data or even the control of radiotherapy equipment.

[0008] In one aspect, the present invention provides a medical instrument including a magnetic resonance imaging system, which is configured to acquire magnetic resonance imaging data from an imaging region. The magnetic resonance imaging system includes an object support configured to support at least a portion of an object in the imaging region. The object support includes a support surface for accommodating the object. The object support includes a radar array, which is specifically embedded below the support surface. In some examples, the radar array can be embedded in the object support. In other embodiments, the support surface is formed by a covering or an attachment, which includes a radar array placed on the object support.

[0009] The magnetic resonance imaging system also includes a radar system for collecting radar signals from the object. The radar system includes a radar array. The medical instrument also includes a motion detection system configured to collect movement signals from the object. In different examples, the motion detection system can take different forms. In one example, the motion detection system is an optical or camera system for measuring the movement or breathing of the object. In other examples, the motion detection system can be, for example, an ultrasound imaging system.

[0010] The medical instrument also includes a memory for storing machine executable instructions and pulse sequence commands. The pulse sequence commands are instructions or data that can be converted into instructions or commands that can be used to control the magnetic resonance imaging system to acquire magnetic resonance imaging data. The medical instrument also includes a processor for controlling the medical instrument. Execution of the machine executable instructions causes the processor to continuously receive radar signals from the radar system. Execution of the machine executable instructions also causes the processor to continuously receive movement signals from the motion detection system.

[0011] The execution of the machine executable instructions also causes the processor to continuously calculate the combined motion signal based on the radar signal and the mobile signal. The radar signal and the mobile signal can be digitally sampled, for example. In this context, the reference to continuous in this article can be interpreted as repeated. For example, the radar signal and the mobile signal can be digitally sampled and the radar signal and the mobile signal can be transmitted to the processor at a specific data rate or in groups of data. When the processor receives the radar signal and the mobile signal, the processor can respond by calculating the combined motion signal.

[0012] Execution of the machine executable instructions further causes the processor to control the magnetic resonance imaging system using the pulse sequence command to acquire magnetic resonance imaging data. The acquisition of the magnetic resonance imaging data is controlled at least in part using the combined motion signal. For example, the combined motion signal can be used to gate the acquisition of the magnetic resonance imaging data so that an image can be made about a specific movement phase (e.g., a cardiac phase or a respiratory phase). In other examples, the movement signal or the combined motion signal can be used to control how the magnetic resonance imaging data is acquired during operation with another portion of the medical instrument.

[0013] This embodiment may be beneficial because the combination of the radar signal with the motion signal may enable a more accurate motion signal to be calculated, or may enable a motion signal that is less sensitive to noise.

[0014] The combined motion signal may for example be used for gating a magnetic resonance acquisition of a cardiac signal and / or a respiratory signal.The combined motion signal may also be useful for gated radiotherapy systems.

[0015] In another embodiment, the radar system is an ultra-wideband or UWB radar system. In other examples, the radar system may be a FMCW radar system. In other examples, the radar system may be a narrowband / dual-band radar system.

[0016] In another embodiment, the combined motion signal includes any of the following: a cardiac phase motion signal, a respiratory phase motion signal, a voluntary motion signal, and combinations thereof. The combined motion signal can be beneficial because the subject's breathing can affect the measurement of the cardiac phase. The combination of the two data types present in the mobile signal and the radar signal can help deconvolve multiple types of motion. The voluntary motion signal can, for example, describe the overall motion or position of the object. As the object moves, it may be difficult for a single modality to accurately measure things such as the cardiac phase or respiratory phase of the object. By combining a camera with a radar signal, for example, it is possible to measure a cardiac phase motion signal and / or respiratory phase motion as the object moves or changes its position.

[0017] In another embodiment, a combined motion signal is calculated by cross-correlating the radar signal with the motion signal, thereby identifying similar signals and rejecting false signals. This embodiment may be beneficial because it may improve the signal-to-noise ratio or reduce errors when calculating the combined motion signal.

[0018] In another embodiment, a combined motion signal is calculated by multiplying the radar signal with the mobile signal to determine when the radar signal and the mobile signal coincide. This can be beneficial because both the radar signal and the mobile signal have amplitudes that can be used as triggers individually. The multiplication of the radar signal with the mobile signal provides a consistent means of combining the two signals. There may be a phase difference or delay between the two signals, but the effect will be consistent. In another embodiment, the combined motion signal is calculated by adding the mobile signal to the radar signal using a corrective phase shift. For example, the Doppler shift of the radar signal can be used to obtain the speed of motion. This can be useful for correcting the phase between the radar signal and the mobile signal.

[0019] Correlation between optical and radar systems

[0020] In another embodiment, a machine learning algorithm is used to continuously calculate the combined motion signal. In different examples, the machine learning algorithm can take different forms. For example, there can be a statistical learning method, which can also be created by fitting a model to the acquired radar signal and mobile signal. In other examples, a neural network using, for example, a convolutional neural network and / or deep learning can be used to process the radar signal and the mobile signal into a combined motion signal. Using a neural network can be particularly beneficial because neural networks are good at recognizing patterns. Therefore, deep learning can be used to combine specific patterns of radar signals and motion signals.

[0021] In another embodiment, the machine executable instructions further cause the processor to receive a preliminary radar signal from a radar system. Execution of the machine executable instructions further causes the processor to receive a preliminary movement signal from a motion detection system. The preliminary movement signal is collected simultaneously with the preliminary radar signal. Execution of the machine executable instructions further causes the processor to receive a heart rate signal from a heart rate monitor. The heart rate signal is collected simultaneously with the preliminary radar signal. Execution of the machine executable instructions further causes the processor to receive a breathing signal from a breathing monitor. The breathing signal is collected simultaneously with the preliminary radar signal.

[0022] Execution of the machine executable instructions also causes the processor to train the machine learning algorithm using the preliminary radar signal, preliminary movement signal, heart rate signal, and breathing signal. This embodiment can be performed for a large number of objects before the examination, or can be performed before a specific object is imaged by the magnetic resonance imaging system. In any case, in this example, the radar signal and the movement signal are compared with independent data (e.g., heart rate signal and breathing signal), so that the machine learning algorithm can be trained directly. For example, the heart rate signal and the breathing signal can be used for output in training the neural network. The preliminary radar signal and the preliminary movement signal can, for example, be for a specific object, or can be obtained from a group of objects used for the training process.

[0023] In another embodiment, the machine learning algorithm is an unsupervised statistical learning algorithm. The execution of the machine executable instructions further causes the processor to train the machine learning algorithm on the fly as the radar signals and mobile signals are received. The statistical learning algorithm may involve fitting a model to the data. The statistical learning algorithm may be adjusted for a specific object, for example, during the acquisition of the radar signals and mobile signals for the specific object.

[0024] In another embodiment, one or more of the movement signal and the radar signal supplies a cardiac motion signal. Another of the movement signal and the radar signal supplies a body motion signal. Execution of the machine executable instructions further causes the processor to calculate a motion vector field using the cardiac motion signal and the body motion signal. The cardiac phase motion signal is denoised using the motion vector field. This embodiment may be beneficial because the overall motion of the subject's body as described by the body motion signal can be used to refine and improve the cardiac motion signal.

[0025] In another embodiment, the motion signal comprises chest motion. The motion detection system comprises a camera for detecting chest motion. This may be beneficial because the subject's breathing may be measured in a contactless manner using the camera.

[0026] Examples of cameras that can be used are eg infrared cameras, color cameras, black and white cameras and three-dimensional or 3D cameras.

[0027] In another embodiment, the camera can also optionally detect the presence or absence of a surface coil on the subject. When chest movement is detected, the chest movement can be detected by measuring direct movement of the subject, by measuring changes in position of clothing worn by the subject, or even by changes in position of a surface coil that has been placed on the subject.

[0028] In another embodiment, the magnetic resonance imaging system further comprises a remotely controllable camera support configured for remotely aiming the camera. Execution of the machine executable instructions further causes the processor to use the radar signal to determine a focus position. Execution of the machine executable instructions further causes the processor to control the remotely controllable camera support to aim the camera at the focus position. This embodiment may be beneficial because the radar system may be useful for detecting general or broad motion of an object. By using the radar system, an optimal position for aiming the camera can be detected. The camera is then aimed at the focus position, and motion data from the camera can then be used to further refine the motion detected by the radar signal.

[0029] In another embodiment, the motion detector system comprises an ultrasound imaging system.Using an ultrasound imaging system may be beneficial because the data acquired by the ultrasound imaging system is complementary to the data acquired by the radar system.

[0030] In another embodiment, the ultrasound imaging system includes an array of ultrasound transducers distributed across a support surface. For example, the ultrasound transducers may be placed around or in between elements of a radar array.

[0031] In another embodiment, the ultrasound imaging system is a HIFU system mounted in a subject support. This embodiment may be beneficial because the HIFU system may be useful for both collecting motion signals and performing sonication on the position of the subject. The combined motion signal may be useful, for example, for targeting or gating sonication of the subject using the HIFU system.

[0032] In another embodiment, the ultrasound imaging system has an adjustable field of view. Execution of the machine executable instructions further causes the processor to use the radar signal to determine a focus position, and control the adjustable field of view so that the focus position is within the adjustable field of view. For example, if there are multiple ultrasound transducers distributed throughout the support service, the radar system can be used to first determine which transducers should be used to image the object, thereby using the ultrasound imaging system to measure the motion signal. This can have the effect of increasing the likelihood that the combined motion signal has less noise and contains a more relevant signal for tracking the motion of the object.

[0033] In another embodiment, the medical instrument further comprises a radiotherapy system. Execution of the machine executable instructions further causes the processor to receive a radiotherapy instruction configured to control the radiotherapy system to irradiate a target area of ​​the subject. Execution of the machine executable instructions further causes the processor to control the radiotherapy system to irradiate the target area using the radiotherapy instruction and the combined motion signal. The combined motion signal is used to modify the radiotherapy instruction and / or to gate irradiation performed by the radiotherapy system. This embodiment can be beneficial because the combined motion signal can be used to improve targeting of the radiotherapy system.

[0034] In another embodiment, the magnetic resonance imaging system is configured to perform a moving bed magnetic resonance imaging protocol. This is a protocol in which the bed is moved into the magnetic resonance imaging system and the magnetic resonance imaging is performed simultaneously or in steps. During the movement of the subject support, both the radar signal and the movement signal can be detected and measured. The signals can be filtered and correlated. In certain positions of the subject support, one or the other of the two signals may be sufficient. This can provide the benefit of improved tracking and motion during a moving bed magnetic resonance imaging protocol.

[0035] In another aspect, the present invention provides a computer program product comprising machine executable instructions configured to be executed by a processor controlling a medical instrument. The medical instrument comprises a magnetic resonance imaging system for acquiring magnetic resonance imaging data from an imaging region. The medical instrument comprises an object support configured to support at least a portion of an object within the imaging region. The object support comprises a support surface for accommodating the object. The object support comprises a radar array embedded below a support surface. The medical instrument further comprises a radar system for acquiring radar signals from the object. The radar system comprises a radar array.

[0036] The medical instrument also includes a motion detection system configured to collect movement signals from the object. The execution of the machine executable instructions also causes the processor to continuously receive radar signals from the radar system. The execution of the machine executable instructions also causes the processor to continuously receive movement signals from the motion detection system. The execution of the machine executable instructions also causes the processor to continuously calculate a combined movement signal based on the radar signal and the movement signal. The execution of the machine executable instructions also causes the processor to control the magnetic resonance imaging system using pulse sequence commands to collect magnetic resonance imaging data. The combined movement signal is used to control the collection of magnetic resonance imaging data. The advantages of this embodiment have been discussed above.

[0037] In another aspect, the present invention provides a method of operating a medical instrument. The medical instrument includes a magnetic resonance imaging system for acquiring magnetic resonance imaging data from an imaging region. The medical instrument includes an object support configured to support at least a portion of an object within the imaging region. The object support includes a support surface for accommodating the object. The object support includes a radar array embedded below the support surface. The medical instrument also includes a radar system for acquiring radar signals from the object. The radar system includes the radar array.

[0038] The medical instrument also includes a motion detection system configured to collect a motion signal from the object. The method includes continuously receiving a radar signal from the radar system. The method also includes continuously receiving a motion signal from the motion detection system. The method also includes continuously calculating a combined motion signal based on the radar signal and the motion signal. The method also includes controlling the magnetic resonance imaging system to collect magnetic resonance imaging data using a pulse sequence command. The combined motion signal is used to control the collection of magnetic resonance imaging data.

[0039] It should be understood that one or more of the aforementioned embodiments of the present invention may be combined as long as the combined embodiments are not mutually exclusive.

[0040] Those skilled in the art will appreciate that aspects of the present invention may be implemented as devices, methods, or computer program products. Therefore, aspects of the present invention may take the form of a complete hardware embodiment, a complete software embodiment (including firmware, resident software, microcode, etc.), or an embodiment that combines software and hardware aspects, all of which are generally referred to herein as "circuits," "modules," or "systems." In addition, aspects of the present invention may take the form of a computer program product implemented in one or more computer-readable media having a computer executable code implemented thereon.

[0041] Any combination of one or more computer-readable media may be utilized. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. As used herein, "computer-readable storage medium" encompasses any tangible storage medium that can store instructions that can be executed by a processor of a computing device. A computer-readable storage medium may be referred to as a computer-readable non-transient storage medium. A computer-readable storage medium may also be referred to as a tangible computer-readable medium. In some embodiments, a computer-readable storage medium may also store data that can be accessed by a processor of a computing device. Examples of computer-readable storage media include, but are not limited to, floppy disks, magnetic hard disk drives, solid-state hard disks, flash memories, USB thumb drives, random access memories (RAM), read-only memories (ROM), optical disks, magneto-optical disks, and register files of processors. Examples of optical disks include compact disks (CDs) and digital versatile disks (DVDs), such as CD-ROMs, CD-RWs, CD-Rs, DVD-ROMs, DVD-RWs, or DVD-R disks. The term "computer-readable storage medium" also refers to various types of recording media that can be accessed by a computer device via a network or communication link. For example, data may be retrieved on a modem, on the Internet, or on a local area network. Computer executable code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0042] A computer readable signal medium may include, for example, a propagated data signal in which a computer executable code is implemented, in baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including, but not limited to, electromagnetic, optical, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that is capable of conveying, propagating, or transmitting a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0043] "Computer memory" or "memory" is an example of a computer-readable storage medium. Computer memory is any memory that can be directly accessed by a processor. Computer storage can be any volatile or non-volatile computer-readable storage medium.

[0044] As used herein, "processor" encompasses an electronic component capable of running a program or machine executable instructions or computer executable code. References to computing devices including "processors" should be interpreted as possibly including more than one processor or processing core. The processor may be, for example, a multi-core processor. The processor may also refer to a collection of processors within a single computer system or distributed between multiple computer systems. The term "computing device" should also be interpreted as possibly referring to a collection or network of multiple computing devices, each of which includes one or more processors. Computer executable code may be executed by multiple processors that may be within the same computing device or may even be distributed on multiple computing devices.

[0045] Computer executable code can include machine executable instructions or programs that cause a processor to perform an aspect of the present invention. Computer executable code for performing operations for various aspects of the present invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​(e.g., Java, Smalltalk, C++, etc.) and conventional procedural programming languages ​​(e.g., C programming language or similar programming languages), and compiled into machine executable instructions. In some instances, the computer executable code can be in the form of a high-level language or in a precompiled form, and can be used in conjunction with an interpreter that generates machine executable instructions in real time.

[0046] The computer executable code may run entirely on the user's computer as a stand-alone software package, partially on the user's computer, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter two scenarios, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0047] Various aspects of the present invention are described with reference to flowchart illustrations and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each frame or part of the frame of a flowchart, diagram and / or block diagram can be implemented by a computer program instruction in the form of computer executable code when appropriate. It should also be understood that when mutually non-exclusive, the frames in different flowcharts, diagrams and / or block diagrams can be combined. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, so that the instructions executed by the processor of a computer or other programmable data processing device create a unit for implementing the function / action specified in one or more frames of a flowchart and / or block diagram.

[0048] These computer program instructions may also be stored in a computer-readable medium that can direct a computer, other programmable data processing apparatus, or other device to function in a specific manner so that the instructions stored in the computer-readable medium produce an article of manufacture that includes instructions for implementing the functions / actions specified in the flowchart and / or one or more block diagram blocks.

[0049] The computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus, or other devices, thereby producing a computer-implemented process, such that the instructions running on the computer or other programmable apparatus provide a process for implementing the functions / actions specified in the flowchart and / or one or more block diagram blocks.

[0050] "User interface" used herein is an interface that allows a user or operator to interact with a computer or computer system. "User interface" may also be referred to as a "human-machine interface device". A user interface may provide information or data to an operator and / or receive information or data from an operator. A user interface may enable the input from an operator to be received by the computer, and may provide output to a user from the computer. In other words, a user interface may allow an operator to control or manipulate a computer, and the interface may allow the computer to indicate the effect of the control or manipulation of the operator. The display of data or information on a display or graphical user interface is an example of providing information to an operator. Receiving data by a keyboard, mouse, tracking ball, touch pad, pointing stick, graphic input board, joystick, game controller, webcam, head mounted device, foot pedal, wired gloves, remote controller, and accelerometer is all examples of user interface components that enable receiving information or data from an operator.

[0051] "Hardware interface" as used herein encompasses an interface that enables a processor of a computer system to interact with and / or control an external computing device and / or apparatus. A hardware interface may allow a processor to send a control signal or instruction to an external computing device and / or apparatus. A hardware interface may also enable a processor to exchange data with an external computing device and / or apparatus. Examples of hardware interfaces include, but are not limited to, a universal serial bus, an IEEE 1394 port, a parallel port, an IEEE 1284 port, a serial port, an RS-232 port, an IEEE-488 port, a Bluetooth connection, a wireless LAN connection, a TCP / IP connection, an Ethernet connection, a control voltage interface, a MIDI interface, an analog input interface, and a digital input interface.

[0052] Magnetic resonance (MR) data is defined herein as the measurements of radio frequency signals emitted by atomic spins recorded by the antenna of a magnetic resonance device during a magnetic resonance imaging scan. Magnetic resonance data or magnetic resonance imaging data is an example of medical image data. A magnetic resonance imaging (MRI) image is defined herein as a two-dimensional or three-dimensional visualization reconstructed from anatomical data contained within the magnetic resonance imaging data. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In the following, preferred embodiments of the present invention will be described by way of example only and with reference to the accompanying drawings, in which:

[0054] Figure 1 An example of a medical instrument is illustrated;

[0055] Figure 2 The diagram shows the operation Figure 1 A flowchart of a method of a medical instrument;

[0056] Figure 3Further examples of medical instruments are illustrated;

[0057] Figure 4 Further examples of medical instruments are illustrated;

[0058] Figure 5 Further examples of medical instruments are illustrated;

[0059] Figure 6 The diagram shows the operation Figure 5 A flowchart of a method of a medical instrument;

[0060] Figure 7 Further examples of medical instruments are illustrated;

[0061] Figure 8 is a flow chart illustrating a method of calculating a combined motion signal;

[0062] Fig. 9 illustrates further examples of medical instruments; and

[0063] Fig.10 A flow chart illustrating a further method of calculating a combined motion signal is shown.

[0064] Reference numerals list

[0065] 100 Medical Instruments

[0066] 102 Magnetic Resonance Imaging System

[0067] 104 Magnets

[0068] 106 Magnet bore

[0069] 108 Imaging Area

[0070] 109 Areas of Interest

[0071] 110 Magnetic Field Gradient Coil

[0072] 112 Magnetic Field Gradient Coil Power Supply

[0073] 114 RF Coil

[0074] 116 transceiver

[0075] 118 objects

[0076] 120 Object Support

[0077] 121 Support surface

[0078] 122 Motion Detection System

[0079] 124 radar system

[0080] 125 radar array

[0081] 126 Computer Systems

[0082] 128 hardware interfaces

[0083] 130 processors

[0084] 132 User Interface

[0085] 134 Computer processor

[0086] 140 machine executable instructions

[0087] 142 pulse sequence commands

[0088] 144 radar signal

[0089] 146 mobile signal

[0090] 148 combined motion signals

[0091] 150 MRI data

[0092] 152 Magnetic resonance imaging

[0093] 154 Machine Learning Algorithms

[0094] 200 Continuously receive radar signals from the radar system

[0095] 202 Continuously receiving motion signals from the motion detection system

[0096] 204 Continuously calculate the combined motion signal based on the radar signal and the mobile signal

[0097] 206 Using pulse sequence commands to control the magnetic resonance imaging system to acquire magnetic resonance imaging data

[0098] 300 Medical instruments

[0099] 322 Camera

[0100] 324 Remote Controlled Camera Bracket

[0101] 346 image data

[0102] 350 focus positions

[0103] 400 Medical Imaging System

[0104] 422 Ultrasound Imaging System

[0105] 424 Ultrasonic transducer

[0106] 446 Ultrasound Data

[0107] 500 Medical Instruments

[0108] 502 Radiotherapy System

[0109] 506 rack

[0110] 508 Radiotherapy Source

[0111] 510 Collimator

[0112] 514 Cryostat

[0113] 516 superconducting coil

[0114] 518 superconducting shielding coil

[0115] 528 Body Coil

[0116] 537 Mechanical Positioning System

[0117] 538 Target Area

[0118] 540 rack rotation axis

[0119] 542 Radiation Beam

[0120] 560 Radiation Therapy Instructions

[0121] 600 receives a radiotherapy treatment configured to control a radiotherapy system to irradiate a target area of ​​a subject.

[0122] instruction

[0123] 602 Using the radiation therapy instructions and the combined motion signal to control the radiation therapy system to irradiate the target area

[0124] 800 camera images

[0125] 802 radar measurement results

[0126] 804 Correlation and / or combination of signals

[0127] 1000 ultrasonic measurement results DETAILED DESCRIPTION

[0128] In these figures, elements with the same reference numerals are either equivalent elements or perform the same function. Elements discussed previously need not be discussed again in subsequent figures if the function is the same.

[0129] Figure 1An example of a medical instrument 100 of a magnetic resonance imaging system 102 with a magnet 104 is shown. The magnet 104 is a superconducting cylindrical type magnet with a bore 106 passing through it. Different types of magnets can also be used; for example, split cylindrical magnets and so-called open magnets can also be used. Split cylindrical magnets are similar to standard cylindrical magnets, except that the cryostat has been divided into two parts to allow access to the isoplane of the magnet, such magnets can be used in conjunction with charged particle beam therapy, for example. Open magnets have two magnet parts, one above the other, with a space between the two magnets sufficient to accommodate the object: the area arrangement of the two parts is similar to that of a Helmholtz coil. Open magnets are popular because the object is less constrained. Inside the cryostat of the cylindrical magnet there is a collection of superconducting coils. Within the bore 106 of the cylindrical magnet 104 there is an imaging zone 108 in which the magnetic field is strong and uniform enough to perform magnetic resonance imaging. A region of interest 109 is shown within the imaging zone 108. Magnetic resonance imaging data is typically acquired for the region of interest. An object 118 is shown supported by an object support 120 such that at least part of the object 118 is within the imaging zone 108 and the region of interest 109.

[0130] Also within the bore 106 of the magnet is a collection of magnetic field gradient coils 110 for acquiring preliminary magnetic resonance imaging data to spatially encode magnetic spins within the imaging zone 108 of the magnet 104. The magnetic field gradient coils 110 are connected to a magnetic field gradient coil power supply 112. The magnetic field gradient coils 110 are intended to be representative. Typically, the magnetic field gradient coils 110 include three independent coil sets, which are used to perform spatial encoding in three orthogonal spatial directions. The magnetic field gradient power supply supplies current to the magnetic field gradient coils. The current supplied to the magnetic field gradient coils 110 is controlled according to time and can be ramped or pulsed.

[0131] Adjacent to the imaging zone 108 is a radio frequency coil 114 for manipulating the orientation of magnetic spins within the imaging zone 108 and for receiving radio transmissions from spins also within the imaging zone 108. The radio frequency antenna may contain multiple coil elements. The radio frequency antenna may also be referred to as a channel or antenna. The radio frequency coil 114 is connected to a radio frequency transceiver 116. The radio frequency coil 114 and the radio frequency transceiver 116 may be replaced by separate transmit and receive coils and separate transmitters and receivers. It should be understood that the radio frequency coil 114 and the radio frequency transceiver 116 are representative. The radio frequency coil 114 is also intended to represent a dedicated transmit antenna and a dedicated receive antenna. Similarly, the transceiver 116 may also represent a separate transmitter and receiver. The radio frequency coil 114 may also have multiple receive / transmit elements, and the radio frequency transceiver 116 may have multiple receive / transmit channels. For example, if a parallel imaging technique such as SENSE is performed, the radio frequency coil 114 will have multiple coil elements.

[0132] An object support 120 is shown supporting an object 118 in an imaging region. The object support 120 has a support surface 121 configured to accommodate the object 118. There is a radar system 124 shown positioned within the object support 120. The radar system 124 also includes a radar array 125 that is below the support surface 121 and is aimed at the object 118. The multiple elements of the radar array 125 enable measurements of the motion of the object 118 to be measured. This includes both internal and external motion of the object 118. Block 122 is intended to represent a motion detection system 122. Other examples of motion detection systems 122 are shown in detail in other figures.

[0133] The magnetic field gradient coil power supply 112, transceiver 116, motion detection system 122, and radar system 124 are shown as being connected to a hardware interface 128 of a computer system 126. The computer system also includes a processor 130, a memory 134, and a user interface 132 that communicate with the hardware system 128. The memory 134 can be any combination of memory accessible to the processor 130. This can include, for example, main memory, cache memory, and non-volatile memory such as flash RAM, a hard drive, or other storage device. In some examples, the memory 134 can be considered a non-transitory computer readable medium.

[0134] The memory 134 is shown as containing machine executable instructions 140. The machine executable instructions 140 enable the processor 130 to control the operation and functions of the magnetic resonance imaging system 100. The machine executable instructions 140 may also enable the processor 130 to perform various data analysis and computational functions. The computer memory 134 is also shown as containing pulse sequence commands 142. The pulse sequence commands are configured to control the magnetic resonance imaging system 100 to acquire a series of magnetic resonance imaging data from the subject 118 according to a magnetic resonance imaging protocol.

[0135] Memory 134 is also shown as containing radar signal 144 collected using radar system 124. Memory 134 is also shown as containing movement signal 146 recorded by motion detection system 122. Memory 134 is also shown as including combined motion signal 148 calculated using radar signal 144 and movement signal 146. Combined motion signal 148 can take different forms, for example, in different examples. It can be a heart signal, a respiratory phase signal, or even a combination of the two. Combined motion signal 148 can also contain details about the overall movement or large movement of object 118.

[0136] The memory 134 is also shown as containing magnetic resonance imaging data 150 acquired by controlling the magnetic resonance imaging system 102 using the pulse sequence commands 142. The memory 134 is also shown as containing a magnetic resonance image 152 reconstructed from the magnetic resonance imaging data 150. The magnetic resonance imaging data 150 may be controlled in part using the combined motion signal 148. For example, the combined motion signal 148 may be used to gate or otherwise adjust control of the magnetic resonance imaging data.

[0137] Memory 134 is also shown as containing an optional machine learning algorithm 154 that may be used to calculate combined motion signal 148 from radar signal 144 and movement signal 146 .

[0138] Figure 2 The diagram shows the operation Figure 1 Flow chart of a method of medical instrument 100 . Figure 2The method shown is used as a control loop. First, in step 200, a radar signal 144 is received. Next, in step 202, a movement signal 146 is received. Steps 200 and 202 can be performed simultaneously or in any order. The radar signal 144 and the movement signal 146 can be received, for example, in the form of digital data. In this case, the radar signal 144 and the movement signal 146 can be collected in discrete data blocks. Although the radar signal 144 and the movement signal 146 are collected discretely, the radar signal 144 and the movement signal 146 can also be collected in a regular or repeated manner, in which case they constitute a continuous collection of data. Next, in step 204, a combined motion signal 148 is calculated based on the radar signal 144 and the movement signal 146. Next, in step 206, the magnetic resonance imaging system 102 is controlled using the pulse sequence command 142 to collect magnetic resonance imaging data 150. The combined motion signal 148 can be used, for example, for gating the collection of magnetic resonance imaging data 150 or for adjusting the pulse sequence command 142 during the collection.

[0139] Figure 3 A further example of a medical instrument 300 is shown. Figure 3 The example shown is similar to Figure 1 The example shown. Figure 3 , the motion detection system is a camera 322. The camera is shown attached to an optional remotely controllable camera mount 324. The remotely controllable camera mount 324 allows the focus position of the camera 322 to be adjusted remotely.

[0140] Memory 134 is shown as containing image data 346. The image data is recorded by camera 322 and is an example of a motion signal. Radar system 124 may be used, for example, to determine which portion of object 118 may be best measured using camera 322. Memory 134 is shown as optionally containing a focus position 350 determined using radar signal 144. Focus position 350 may then be used to generate a command to cause remotely controllable camera mount 324 to adjust the position of camera 322.

[0141] In this example, radio frequency coil 114 is a surface coil that has been placed on the chest of subject 118. Camera 322 may, for example, measure image data 346 and then convert image data 346 into movement signal 146 by noting the changes in position of radio frequency coil 114 that occur as subject 118 breathes. In other examples, camera 322 may look directly at the chest of subject 118, or may track the movement of clothing worn by subject 118.

[0142] Figure 4 A further example of a medical instrument 400 is shown. Figure 4 The example shown is similar to Figure 11. The motion detection system 134 is an example of a medical instrument in the present invention. In this example, the motion detection system is an ultrasound imaging system 422. There are ultrasound transducers 424 dispersed within the object support 120. The connection between the ultrasound imaging system 422 and the ultrasound transducers 424 is not shown. The memory 134 is shown as containing ultrasound data 446 acquired using the ultrasound imaging system 422 (e.g., a Doppler imaging ultrasound imaging system). The ultrasound data 446 is an example of the movement signal 146.

[0143] To determine which ultrasonic transducers 424 should be used to measure ultrasonic data, the radar system 124 can be used to initially determine a focus position 350. The focus position 350 can be used to select which ultrasonic transducers 424 to use to measure ultrasonic data 446.

[0144] Figure 5 A further example of a medical instrument 500 is illustrated. Figure 5 The example shown is similar to Figure 3 The example shown differs in that the medical apparatus also includes a radiation therapy system 502. In this particular example, the radiation therapy system is a LINAC, but other radiation therapy systems may be substituted for the LINAC system.

[0145] The radiation therapy system 502 includes a gantry 506 and a radiation therapy source 508. The gantry 506 is used to rotate the radiation therapy source 508 about a gantry rotation axis 540. A collimator 510 is adjacent to the radiation therapy source 508.

[0146] The magnet 112 shown in this embodiment is a standard cylindrical superconducting magnet. The magnet 112 has a cryostat 514 with superconducting coils 516 within the cryostat 514. The cryostat also has superconducting shielding coils 518 within it.

[0147] like Figure 1 As shown, there is a magnetic resonance coil 114 connected to a transceiver 116. Figure 5 Also shown is an optional body coil 528 attached to the transceiver.

[0148] The subject support 120 may be positioned by an optional mechanical positioning system 537. Within the subject 118 is a target zone 538. In this particular embodiment, the gantry rotation axis 540 is coaxial with the cylindrical axis of the magnet 104. The subject support 120 has been positioned so that the target zone 538 is located on the gantry rotation axis 540. The radiation source 508 is shown as generating a radiation beam 542 that passes through the collimator 510 and through the target zone 538. As the radiation source 508 rotates about the axis 540, the radiation beam 542 targets the target zone 538. The radiation beam 542 passes through the cryostat 514 of the magnet.

[0149] The mechanical positioning system 537 and the radiation therapy system 502 are shown as being additionally connected to the hardware interface 128 of the computer system 126 .

[0150] The computer memory 134 is also shown as containing radiation therapy instructions 560. Radiation therapy instructions are instructions or commands that can be converted into commands that can control the radiation therapy system 502 to irradiate the target zone 538. The combined motion signal 148 can be used to modify or gate the execution of the radiation therapy instructions 560.

[0151] Figure 6 The diagram shows the operation Figure 5 Flow chart of a method for a medical device 500. First, in step 600, a radiation therapy instruction 560 is received. Next, the method proceeds to Figure 2 After performing step 206, the method proceeds to step 602, where the radiation therapy instructions 560 and the combined motion signal 148 are used to control the radiation therapy system to irradiate the target zone 538. For example, the combined motion signal 148 can be used to gate the irradiation of the target zone 538, or can also be used to adjust the position of the target zone 538 when the subject 118 moves voluntarily or involuntarily.

[0152] High quality triggering in medical imaging (particularly MR) is useful for a large number of examinations (e.g. cardiac imaging, abdominal imaging or pelvic imaging). The trigger signal (combined motion signal) for the imaging sequence (pulse sequence command) can be executed at equal exhalation states or equal points during the cardiac cycle, resulting in higher image quality. Typically, vital signs are recorded using dedicated sensors, which are not only expensive but also prone to errors and misplacement. In addition, overall patient motion is often a problem, especially during MR imaging, when scans can last several minutes and examinations can take up to an hour.

[0153] Some examples eliminate contact sensors for cardiac monitoring (e.g., breathing belts or PPU sensors) and replace them with two non-contact methods for vital sign detection. It has been previously demonstrated that non-contact methods are at least comparable to conventional sensors, but are cheaper and more reliable. In addition, combining radar with optical detection technology can improve signal quality using cross-correlation between systems, improved calibration schemes, or (spatial) guidance of one system against the other. For example, radar is able to penetrate the body and is better suited than cameras to sense the movement of internal organs. On the other hand, cameras are better suited to sensing abnormal events (e.g., overall patient movement) during which radar signals are unreliable.

[0154] Examples might include an array of inexpensive (ultra-wideband) radar sensors in or under the patient bed of an imaging machine and an optical or infrared camera close to the bore that views the patient during imaging.

[0155] Both systems are connected to a computer which derives the respiratory and / or cardiac signals from the raw data. Suitable algorithms are available for the optical part as well as for the radar part.

[0156] While both entities are now capable of producing vital sign data (radar signal and motion signal), these signals can be combined to, for example, derive a better signal-to-noise ratio, or, for example, the radar array can provide the optical system with a region of interest that can be magnified to produce the best possible output, rather than monitoring a larger area with a relatively low signal.

[0157] Different groups have demonstrated ultra-wideband (UWB) radar and optical systems for vital sign detection, all showing that such a system is feasible. For the optical part, the system can include a camera with suitable optics located close to the bore, and software algorithms to calculate breathing signals from the movement of features in the video stream or heart signals from changes in the patient's skin color in the video.

[0158] The radar array system can be conveniently located in or under the patient bed, allowing greater coverage of the patient's upper body. Systems operating at different frequencies in the GHz range as well as ultra-wideband solutions have been demonstrated. Respiratory or cardiac signals can be calculated from reflections or time-of-flight measurements in the body.

[0159] To derive and improve breathing triggers, the system can work in the following way:

[0160] Example 1:

[0161] Both systems provide respiration curves and trigger points derived from video and radar measurements.

[0162] The independent measurements are then linked and triggers for improvement are generated.

[0163] Example 2:

[0164] Both systems provide respiration curves and trigger points derived from video and radar measurements.

[0165] The area with the best SNR is determined in the spatially resolved radar data and the coordinates are transferred to the optical system.

[0166] Adjusting the camera view to this ROI (angle of view, zoom, exposure...) can generate higher quality breathing curves.

[0167] Figure 7 Additional views of a medical imaging system 300 are shown. Figure 7 In the example shown, the radar sensors 125 are positioned in an array-like manner in or below the subject support 120. Additionally, one or more cameras 322 may observe the patient or subject 118 in the bore 106 of the magnet 104.

[0168] Figure 8 A flow chart showing the signal flow for calculating the combined motion signal is shown. The motion shows a stream of camera images 800 received from camera 322 and radar measurements 802 for each sensor 125 in the array. The signals are then processed, such as by a computer 126 or workstation, to analyze the radar signal and video. The result of this processing is a motion signal or image data 346 or video stream. Radar data 144 is also generated. Block 804 shows that the signals 346 and 144 are correlated and combined. The output of block 804 is the combined motion signal 148. In Figure 8 In the MR, the inputs from two independent systems are analyzed. Then, either an improved trigger signal is generated using, for example, correlation of the signals, or the output of one system is used to set a region of interest for the other device, thereby improving the overall signal quality. The workstation for radar signal and video analysis can also be replaced by a local DSP processing unit located in or near the MR bore or integrated in the patient bed.

[0169] As an alternative to optical sensors (e.g., cameras), ultrasound systems can also be used. Different groups have demonstrated (UWB) radar and Doppler ultrasound (DUS) (ultrasound imaging systems) for vital sign detection, both of which show that such systems are feasible. Ultrasound sensors generate acoustic signals and detect returning signals. Doppler ultrasound (DUS) reflects the physiological activity of the heart in terms of blood flow and heart wall motion, and can therefore monitor the cardiac cycle directly in real time. In addition, depending on the position of the transducer, the DUS signal corresponds to different times in the cardiac cycle, potentially providing more precise information for cardiac triggering than a conventional ECG. Both methods can be used simultaneously and provide better vital sign recording and triggering signals.

[0170] Examples may include an array of inexpensive (ultra-wideband) radar sensors in or under the patient's bed or integrated in the RF coil of an imaging machine and an ultrasound detection system (DUS). Both systems are connected to a computer that derives respiratory and / or cardiac signals from the raw data. Suitable algorithms are available for the DUS and radar parts.

[0171] While both entities can produce vital sign data, the signals can also be combined, for example to derive a better signal-to-noise ratio or for steering purposes. Thus, the radar array can provide a DUS system with a region of interest that zooms in to detect organ-specific motion (heart, lungs, liver) to produce the best or improved output possible, rather than monitoring a larger area with a relatively low signal.

[0172] For the ultrasound (US) part, the sensor includes a local US sensor array and a software algorithm, which is integrated in a gel pad to provide contact with the patient's skin, and the software algorithm calculates the respiratory signal based on the feature movement in the video stream or calculates the cardiac signal based on the patient's skin color changes in the video.

[0173] The radar array system can be conveniently located near the US sensor, either in or under the patient bed, or integrated in the RF coil, allowing greater coverage of the patient's upper body. Systems operating at different frequencies in the GHz range as well as ultra-wideband solutions have been demonstrated. Organ motion signals or cardiac signals can be calculated from reflections or time-of-flight measurements in the body.

[0174] To derive and improve breathing triggers, the system can work in the following way:

[0175] Example 1:

[0176] Both systems provide respiration curves and trigger points derived from ultrasound and radar measurements.

[0177] The independent measurements are then linked and triggers for improvement are generated.

[0178] Example 2:

[0179] Both systems provide respiration curves and trigger points derived from ultrasound and radar measurements.

[0180] The area with the best SNR is determined in the spatially resolved radar data and the coordinates are handed over to the ultrasound system, which then detects vital signs locally with a high SNR.

[0181] When the digital RXE module is located in the RF coil, the digital RXE module already present in the coil can be utilized to handle data processing of the US sensor data and power supply.

[0182] Fig. 9A further view of a medical instrument 400 is shown. In the top view, an object 118 is shown located on an object support 120. There is an array of radar elements 125. In this example, there are ultrasound transducers 424 located above and inside each of the radar elements 125. The radar sensors and US sensors are located in an array inside or below the patient support or are integrated in the RF coil.

[0183] Fig.10 A flow chart illustrating the signal flow in the process of making a combined motion signal 148 is shown. The input is the ultrasound data 1000 measured by each ultrasound transducer. Furthermore, the input is the radar measurement results of each radar element 125. These inputs are then put into a local DSP processor or computer 126. Its output is the ultrasound data 446 and the radar signal 144. These data and signals are then correlated in box 804. The output is the combined motion signal 148. The inputs from these two independent systems are analyzed. Then, either the correlation of the signals is used, for example, to generate an improved trigger signal, or the output of one system is used to set a region of interest for another device, thereby improving the overall signal quality. The workstation for radar signal and ultrasound analysis can also be replaced by a local DSP processing unit located in or near the MR chamber or integrated in the patient bed.

[0184] In some examples, the medical instrument also includes a machine learning module with deep learning capabilities, the machine learning module adapted to receive the sensed radar signal and the optical motion signal. Deep learning methods are designed to learn feature hierarchies having features at higher levels of the hierarchy formed from lower level feature components. They can include learning methods for a wide array of deep architectures, including neural networks with hidden layers and graphical models with levels of hidden variables.

[0185] Unsupervised pre-training makes learning deep architectures more efficient. Such pre-training serves as a kind of network pre-conditioner, thereby bringing the parameter values ​​into an appropriate range for further supervised training and initializing the model to a point in parameter space, which in a sense makes the optimization process more efficient, achieving a lower minimum of the empirical cost function.

[0186] In one example, the radar signal and the optical signal are acquired simultaneously. This allows for real-time correlation and also allows corrections to be made using the other signal.

[0187] In one example, one of the radar system and the motion detection system, preferably the radar device, is coupled to the optical system so that information about where the spatial focusing is done is sent. The optical system can additionally generate information for checking whether the coil is placed.

[0188] In one example, two sensors detect the moving bed signal simultaneously, and the moving bed signal is filtered and correlated, but in certain areas, one of the two signals may be sufficient.

[0189] In one example, one of the radar system and the motion detection system delivers motion detection results while the other supplies the cardiac signal. Simultaneous detection and correlation allows the generation of a motion vector field that can be used to denoise the cardiac trigger signal.

[0190] In another example, the movement of internal organs can be inferred from radar, and surface movement (skin, clothing, coils, etc.) can be detected by optical devices such as cameras.

[0191] In some examples, possible correlation mechanisms between radar signals and mobile signals may include one or more of the following:

[0192] Cross-correlation of radar signals with optical signals in order to check for similarity of signals and find false positive / negative results).

[0193] The trigger curves generated from the two sources are multiplied together. When the signals coincide (in terms of time), a curve is produced with clear maxima and minima. This curve can be used to measure the possible delay between the systems (depending on the area of ​​the body that each system is to process).

[0194] Signal nulling: Subtract a scaled version of both the signal and the time shift so that the remaining signal is essentially zero. This can also be used for delay measurements. Once the delay is known, a determined time shift can be added to the two signals to improve the SNR.

[0195] While the invention has been illustrated and described in detail in the drawings and foregoing description, such illustration and description are to be considered illustrative or exemplary and not restrictive; the invention is not limited to the disclosed embodiments.

[0196] Those skilled in the art can understand and implement other variations of the disclosed embodiments when practicing the claimed invention by studying the drawings, the disclosure and the claims. In the claims, the word "comprising" does not exclude other elements or steps, and the words "one" or "an" do not exclude multiple. A single processor or other unit can implement the functions of several items recorded in the claims. Although certain measures are recorded in mutually different dependent claims, this does not indicate that a combination of these measures cannot be used to advantage. The computer program may be stored / distributed on a suitable medium, for example, an optical storage medium or solid-state medium supplied together with other hardware or as part of other hardware, but may also be distributed in other forms, for example, via the Internet or other wired or wireless telecommunications systems. Any reference numerals in the claims should not be interpreted as limiting the scope.

Claims

1. A medical apparatus (100, 300, 400, 500) comprising a magnetic resonance imaging system (102) for acquiring magnetic resonance imaging data (150) from an imaging region (108), wherein: The medical instrument further comprises: a subject support (120) configured to support at least a portion of a subject within the imaging region, wherein the subject support comprises a support surface (121) for receiving the subject; a radar system (124) located within the object support and for acquiring radar signals (144) from the object, wherein the radar system comprises a radar array arranged to be embedded below the support surface and to enable measurement of movement of the object; a motion detection system (122) configured to collect a movement signal (146) from the object; a memory (134) for storing machine executable instructions (140) and pulse sequence commands (142); a processor (130) for controlling the medical instrument, The execution of the machine executable instructions causes the processor to perform the following operations: continuously (200) receiving the radar signal from the radar system; continuously (202) receiving the movement signal from the motion detection system; continuously (204) calculating a combined motion signal (148) based on the radar signal and the motion signal; and The magnetic resonance imaging system is controlled (206) using the pulse sequence commands to acquire the magnetic resonance imaging data, wherein the acquisition of the magnetic resonance imaging data is controlled using the combined motion signal.

2. The medical instrument according to claim 1, wherein: The combined motion signal includes any one of the following: a cardiac phase motion signal, a respiratory phase motion signal, a voluntary motion signal, and a combination thereof.

3. The medical instrument according to claim 2, wherein: The combined motion signal is calculated by any of the following: cross-correlating the radar signal with the motion signal to identify similar signals and reject false signals; multiplying the radar signal and the motion signal to determine when the radar signal and the motion signal coincide; and The motion signal is added to the radar signal using a corrective phase shift.

4. The medical instrument according to claim 3, wherein: The combined motion signal is continuously calculated using a machine learning algorithm (154).

5. The medical instrument according to claim 4, wherein: Execution of the machine executable instructions further causes the processor to: receiving a preliminary radar signal from the radar system; receiving a preliminary motion signal from the motion detection system, wherein the preliminary motion signal and the preliminary radar signal are collected simultaneously; receiving a heart rate signal from a heart rate monitor, wherein the heart rate signal and the preliminary radar signal are collected simultaneously; receiving a breathing signal from a breathing monitor, wherein the breathing signal is acquired simultaneously with the preliminary radar signal; and The machine learning algorithm is trained using the preliminary radar signal, the preliminary movement signal, the heart rate signal, and the breathing signal.

6. The medical instrument according to claim 4, wherein: The machine learning algorithm is an unsupervised statistical learning algorithm, and wherein execution of the machine executable instructions further causes the processor to train the machine learning algorithm on the fly as the radar signal and the mobile signal are received.

7. The medical instrument according to claim 2 or 3, wherein: One of the movement signal and the radar signal supplies a cardiac motion signal, and the other of the movement signal and the radar signal supplies a body motion signal, wherein execution of the machine-executable instructions further causes the processor to calculate a motion vector field using the cardiac motion signal and the body motion signal, and wherein the cardiac motion signal is denoised using the motion vector field.

8. The medical instrument according to claim 1, wherein: The motion signal comprises chest motion, and wherein the motion detection system comprises a camera for detecting the chest motion.

9. The medical instrument according to claim 8, wherein: The magnetic resonance imaging system also includes a remotely controllable camera support (324) configured to remotely aim the camera, wherein execution of the machine executable instructions further causes the processor to: using the radar signal to determine a focus position (350); and The remotely controllable camera mount is controlled to align the camera to the focus position.

10. The medical instrument according to claim 1, wherein: The motion detector system includes an ultrasound imaging system (422).

11. The medical instrument according to claim 10, wherein: The ultrasound imaging system comprises an array of ultrasound transducers distributed across the support surface, or the ultrasound imaging system is a HIFU system mounted in the subject support.

12. The medical instrument according to claim 10 or 11, wherein: The ultrasound imaging system has an adjustable field of view, wherein execution of the machine executable instructions further causes the processor to: using the radar signal to determine a focus position (350); and The adjustable field of view is controlled so that the focus position is within the adjustable field of view.

13. The medical instrument according to claim 1, wherein: The medical apparatus also includes a radiation therapy system, wherein execution of the machine executable instructions further causes the processor to: receiving (600) radiation therapy instructions configured to control the radiation therapy system to irradiate a target area of ​​the subject; and The radiation therapy system is controlled (602) to irradiate the target zone using the radiation therapy instructions and the combined motion signal, wherein the combined motion signal is used to modify the radiation therapy instructions and / or to gate irradiation by the radiation therapy system.

14. A computer program product comprising machine executable instructions (140) configured to control a medical instrument (100, 300, 400, 500), wherein: The medical instrument comprises a magnetic resonance imaging system (102) for acquiring magnetic resonance imaging data (150) from an imaging zone (108), wherein the medical instrument comprises a subject support (120) configured to support at least a portion of a subject within the imaging zone, wherein the subject support comprises a support surface (121) for receiving the subject, wherein the medical instrument further comprises a radar system (124) located within the subject support and for acquiring radar signals from the subject, wherein the radar system comprises a radar array arranged to be embedded below the support surface and enabling measurement of movement of the subject, wherein the medical instrument further comprises a motion detection system (122) configured to acquire movement signals (146) from the subject, The execution of the machine executable instructions causes the processor to perform the following operations: continuously (200) receiving the radar signal from the radar system; continuously (202) receiving the movement signal from the motion detection system; continuously (204) calculating a combined motion signal (148) based on the radar signal and the motion signal; and The magnetic resonance imaging system is controlled (206) using pulse sequence commands to acquire the magnetic resonance imaging data, wherein the acquisition of the magnetic resonance imaging data is controlled using the combined motion signal.

15. A method of operating a medical instrument (100, 300, 400, 500), wherein: The medical instrument comprises a magnetic resonance imaging system (102) for acquiring magnetic resonance imaging data (150) from an imaging zone (108), wherein the medical instrument comprises a subject support (120) configured to support at least a portion of a subject within the imaging zone, wherein the subject support comprises a support surface (121) for receiving the subject, wherein the medical instrument further comprises a radar system (124) located within the subject support and for acquiring radar signals from the subject, wherein the radar system comprises a radar array arranged to be embedded below the support surface and enabling measurement of movement of the subject, wherein the medical instrument further comprises a motion detection system (122) configured to acquire movement signals (146) from the subject, wherein the method comprises: continuously (200) receiving the radar signal from the radar system; continuously (202) receiving the movement signal from the motion detection system; continuously (204) calculating a combined motion signal (148) based on the radar signal and the motion signal; and The magnetic resonance imaging system is controlled (206) using pulse sequence commands to acquire the magnetic resonance imaging data, wherein the acquisition of the magnetic resonance imaging data is controlled using the combined motion signal.

Images