COMBINED X-RAY SYSTEM AND PILOT TONE SYSTEM

Abstract

Disclosed is an X-ray system (100, 700) configured for acquiring medical imaging data (134) from a subject (102) at least partially within an imaging zone (105). The X-ray system comprises a memory (128) storing machine executable instructions (130). The X-ray system further comprises a processor (122) configured for controlling the X-ray system. The X-ray system further comprises a pilot tone system (106), wherein the pilot tone 5 system comprises a radio frequency system (108) comprising multiple transmit channel (110) and multiple receive channel (112). The multiple transmit channel is configured for transmitting multiple pilot tone signal (136) via multiple transmit coil (114). The multiple receive channel is configured for receiving pilot tone data (138) via multiple receive coil (116). Execution of the machine executable instructions causes the processor to: transmit 10 (202) the multiple pilot tone signal by controlling the multiple transmit channel; acquire (204) the pilot tone data by controlling the multiple receive channel; and determine (206) a motion state (140, 700, 700′, 702, 702′) of the subject using the pilot tone data.

Claims

1. An X-ray system configured for acquiring medical imaging data from a subject at least partially within an imaging zone, the X-ray system comprising: a memory for storing machine executable instructions; a processor configured for controlling the X-ray system; and a pilot tone system, wherein the pilot tone system comprises a radio frequency system comprising multiple transmit channels and multiple receive channels, wherein the multiple transmit channels are configured for transmitting multi-channel pilot tone signals via multiple transmit coils, wherein the multiple receive channels are configured for receiving multi-channel pilot tone data via multiple receive coils, wherein execution of the machine executable instructions causes the processor to: transmit the multi-channel pilot tone signals by controlling the multiple transmit channels; acquire the multi-channel pilot tone data by controlling the multiple receive channels; and determine a motion state of the subject using the multi-channel pilot tone data.

2. The X-ray system of claim 1, wherein the radio frequency system is configured for encoding each of the multi-channel pilot tone signals using at least one of: frequency encoding, phase encoding, complex modulating, Code Division Multiple Access (CDMA) encoding, and combinations thereof.

3. The X-ray system of claim 1, wherein the motion state is at least one of: a subject motion location; a motion vector; a subject motion classification; a breathing state; a heart motion state; a translation vector descriptive of at least a portion of the subject; a rotation descriptive of at least a portion of the subject; and combinations thereof.

4. The X-ray system of claim 1, wherein execution of the machine executable instructions causes the processor to determine the motion state using at least one of: using a recurrent neural network configured for receiving the multi-channel pilot tone data and the at least one multi-channel pilot tone signal and for outputting the motion state; detecting a distance between the subject and each of the at least one receive coils; using digital filtering; using principal component analysis; and combinations thereof.

5. The X-ray system of claim 1, wherein execution of the machine executable instructions further causes the processor to control the X-ray system to acquire the medical imaging data during acquisition of the multi-channel pilot tone data.

6. The X-ray system of claim 1, wherein execution of the machine executable instructions further causer the processor to: reconstruct a medical image using the medical imaging data; and correct the reconstruction of the tomographic medical image using the motion state of the subject.

7. The X-ray system of claim 5, wherein execution of the machine executable instructions further causes the processor to perform gate acquisition of the medical imaging data using the motion state of the subject.

8. The X-ray system of claim 5, wherein execution of the machine executable instructions further causes the processor to modify acquisition of the medical imaging data using the motion state of the subject.

9. (canceled)

10. The X-ray system of claim 1, further comprising a subject support for supporting at least a portion of the subject in the imaging zone, wherein the multiple transmit coils and the multiple receive coils are integrated into the subject support.

11. The X-ray system of claim 1, wherein the X-ray system is an X-ray computed tomography system.

12. (canceled)

13. A method for operating an X-ray system configured for acquiring medical imaging data from a subject at least partially within an imaging zone, the method comprising: providing a pilot tone system, wherein the pilot tone system comprises a radio frequency system comprising multiple transmit channels and multiple receive channels, wherein the multiple transmit channels are configured for transmitting multi-channel pilot tone signals via multiple transmit coils, wherein the multiple receive channels are configured for receiving multi-channel pilot tone data via multiple receive coils; transmitting the multi-channel pilot tone signals by controlling the multiple transmit channels; acquiring the multi-channel pilot tone data by controlling the multiple receive channels to receive the multi-channel pilot tone data; and determining a motion state of the subject using the multi-channel pilot tone data.

14. A non-transitory computer-readable medium having stored thereon instructions for causing processing circuitry to execute a method for operating an X-ray system configured for acquiring medical imaging data from a subject at least partially within an imaging zone, the method comprising: providing a pilot tone system, wherein the pilot tone system comprises a radio frequency system comprising multiple transmit channels and multiple receive channels, wherein the multiple transmit channels are configured for transmitting multi-channel pilot tone signals via multiple transmit coils, wherein the multiple receive channels are configured for receiving multi-channel pilot tone data via multiple receive coils; transmitting the multi-channel pilot tone signals by controlling the multiple transmit channels; acquiring the multi-channel pilot tone data by controlling the multiple receive channels to receive the multi-channel pilot tone data; and determining a motion state of the subject using the multi-channel pilot tone data.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In the following preferred embodiments of the invention will be described, by way of example only, and with reference to the drawings in which:

[0056] FIG. 1 illustrates an example of an X-ray system;

[0057] FIG. 2 shows a flow chart which illustrates a method of operating the X-ray system of FIG. 1;

[0058] FIG. 3 shows a flow chart which illustrates a further method of operating the X-ray system of FIG. 1;

[0059] FIG. 4 shows a flow chart which illustrates a further method of operating the X-ray system of FIG. 1;

[0060] FIG. 5 illustrates an example of multi-channel pilot tone data;

[0061] FIG. 6 illustrates a further example of an X-ray system;

[0062] FIG. 7 illustrates an example of a motion state determined using multi-channel pilot tone data;

[0063] FIG. 8 illustrates an example of a magnetic resonance imaging system;

[0064] FIG. 9 shows a flow chart which illustrates an example of a magnetic resonance imaging system; and

[0065] FIG. 10 illustrates an example of software system for a medical system.

DETAILED DESCRIPTION OF THE EMBODIMENTS

[0066] Like numbered elements in these figures are either equivalent elements or perform the same function. Elements which have been discussed previously will not necessarily be discussed in later figures if the function is equivalent.

[0067] FIG. 1 illustrates an example of an X-ray system. In this example the X-ray system is a computed tomography system or CT system. However, this system depicted in FIG. 1 may also be for example a system for acquiring two-dimensional X-ray images such as a conventional X-ray system or a fluoroscope. The X-ray system 100 further comprises a computed tomography gantry 101 which has a bore 103. Within the bore is shown a subject 102 reposing on a subject support 104. The computed tomography gantry 101 has an imaging zone 105 where medical imaging data can be acquired.

[0068] The X-ray system 100 is shown as having a pilot tone system 106. The pilot tone system 106 comprises a radio-frequency system 108 that has at least one transmit channel 110 and at least one receive channel 112. The at least one transmit channel 110 is connected to at least one transmit channel 114. The at least one receive channel 112 is connected to at least one receive coil 116. In this example the at least one transmit coil 114 and the at least one receive coil 116 are built into the subject support 104. In other examples the coils 114, 116 could be placed in alternative locations such as supports surrounding the subject 102 or even in some instances adjacent or on the subject.

[0069] The X-ray system 100 is shown as further comprising a computer 120. The computer 120 comprises a processor 122. The processor 122 is intended to represent one or more processor or processing cores. The processor 122 could also be distributed amongst multiple computer systems 120. The processor 122 is shown as being connected to a hardware interface 124. The hardware interface 124 enables the processor 122 to send and receive commands and data to other components of the X-ray system 100. In some instances, the hardware interface 124 may for example be a network interface and enable the processor 122 to exchange data with other computer systems. The processor 122 is further shown as being connected to a user interface 126 and a memory 128.

[0070] The memory 128 may be any combination of memory which is accessible to the processor 122. This may include such things as main memory, cached memory, and also non-volatile memory such as flash RAM, hard drives, or other storage devices. In some examples the memory 128 may be considered to be a non-transitory computer-readable medium.

[0071] The memory 128 is shown as having machine-executable instructions 130. The machine-executable instructions 130 enable the processor 122 to control the operation and function of the X-ray system. The memory 128 is shown as containing control commands 132. The control commands may for instance be the specific commands for a particular imaging protocol to acquire medical imaging data 134. The memory 128 is shown as containing medical imaging data 134 that was acquired by controlling the X-ray system with the control commands 132. In some examples the control commands 132 may be incorporated into the machine-executable instructions 130. The memory 128 is further shown as containing a pilot tone signal 136 that may be transmitted using the at least one transmit channel 110.

[0072] The memory 128 is further shown as containing pilot tone data 138 that was received within the at least one receive channel 112 in response to transmitting the pilot tone signal 136. In some examples the pilot tone signal 136 may be multiple unique pilot tone signals 136 that may for example be encoded differently as was disclosed previously. The pilot tone data 138 may likewise be multi-channel pilot tone data. The memory 128 is further shown as containing a motion state 140 that was derived from at least the pilot tone data 138. The memory 128 may for example contain a motion state model 142.

[0073] The motion state model 142 may for example take the pilot tone 138 as input and optionally the pilot tone signal 136 to determine the motion state 140. The motion state model 142 may be implemented in different ways. In one example it may for example be a recurrent neural network, a convolutional neural network, a filter or other various models. The memory 128 is further shown as containing a medical image 144. The medical image 144 was reconstructed from the medical imaging data 134.

[0074] FIG. 2 shows a flowchart which illustrates a method of operating the X-ray system 100 of FIG. 1. First in step 200 the X-ray system is controlled to acquire the medical imaging data 134. As step 200 is performed steps 202, 204, and 206 are also performed. In step 202 the at least one pilot tone signal 136 is transmitted by controlling the at least one transmit channel 110. Next in step 204 the pilot tone data 138 is acquired by controlling the at least one receive channel 112. Finally, in step 206, the motion state 140 of the subject 102 is determined using the pilot tone data 138.

[0075] FIG. 3 illustrates an alternative method of operating the X-ray system 100 of FIG. 1. The method illustrated in FIG. 3 is similar to the method illustrated in FIG. 2 with the addition of several additional steps. Steps 200, 202, 204, 206 are performed as before. In this example step 206 may be performed after steps 200, 202, 204 are completely performed. Next in step 300 the medical image 144 is reconstructed using the medical imaging data 134. Finally, in step 302 the reconstruction of the medical image 144 is corrected using the motion state 140. This may for example be performed in different ways.

[0076] The motion state 140 could for example, if it is monitoring the heart or breathing phase, to divide the medical imaging data 134 into different bins and produce different images 144. In other examples if the motion state 140 is more detailed various portions of the medical imaging data 134 may be corrected and using during the reconstruction of the medical image 144. The method in FIG. 3 is an example of using the motion state 140 to perform retrospective correction of the medical image 144.

[0077] FIG. 4 illustrates a further example of a method of operating the X-ray system 100 of FIG. 1. The method in FIG. 4 is also similar to the method illustrated in FIG. 2. Steps 200, 202, 204, 206 are performed as before. In the example in FIG. 4 the determination of the motion state is done during the acquisition of the medical imaging data 134. In step 400 the medical imaging data is used to modify the acquisition of the medical imaging data. This could for example be used for changing the alignment or region which is imaged as well as to gate the acquisition of the medical imaging data.

[0078] Disclosed is a motion detection method, which may use distinct frequency, multi frequency or broadband signal sources for x-ray or computed tomography (CT) scanners to correct for motion and synchronize the scanner for cardiac imaging using multi-RF reference signals. The proposed method can substitute ECG triggering or the additional data is used to improve reconstruction, reduce radiation dose and improve workflow for autonomous imaging.

[0079] CT scans may use a number of input parameters and proper scan preparation. Depending on body size, body weight, patient position and anatomy to be scanned a protocol is chosen and modified to fit the patient. Typically, these data have to be entered manually. Physiology parameters (e.g. necessary for triggering scans or gating) are typically measured using dedicated sensors. It has been demonstrated recently, that relevant parameters can be deduced from live video-streams of a camera observing the patient during scanning. During a CT procedure the patient is covered by clothes. Consequently, camera images are of limited use.

[0080] Pilot Tones are a contactless, electromagnetic navigators that offers monitoring of motion independently of the MR or CT acquisition. Generation and acquisition of Pilot Tone signals, can be done using, already existing, system integrated parts, such as MR local coils which would be used for magnetic resonance imaging.

[0081] Potential benefits and/or applications may include one or more of the following: [0082] ECG-free detection of heartbeats and breathing [0083] Separation and Quantification of Head—Body Motion [0084] Derive trigger for Cardiac and Respiratory Motion [0085] Applications for MR LINAC-Radiotherapy [0086] Pilot tone/RF reference may be useful for accelerating patient preparation in order to increase quality and improve cost-effectiveness. [0087] provide a substitute for ECG electrodes [0088] reduce Extra workflow [0089] Reduce X-ray dose [0090] correct for or compensate for motion due to uncooperative subject [0091] provide feedback for patient [0092] Track subject motion through covers and clothes.

[0093] Examples may use pilot tone signals for X-Ray or CT scanner. In one example, the digital pilot signal antennas are located/integrated in the patient table.

[0094] For autonomous imaging using X-Ray the system may continuously monitor the 3D position. X-Radiation/imaging is triggered when there is no motion/movement detected or expected. The system allows body positioning during imaging or between imaging sequences or replacing a certain position.

[0095] For CT X-Ray beam is switched off during motion and system detects displacements from original position resulting in less dose.

[0096] In one example, the pilot tone signal may be monitored for active patient feedback. The patient/subject can reposition himself or the patient can align his position using a motion/position feedback monitor/sensor In another example, the 3D/4D information from the pilot tone data may be included in the reconstruction.

[0097] In another example separate transmit and receive antennas and digital transmitters and receivers are used to allow to translate motion into complex 4 D datasets.

[0098] In another example, the data can also feed a convolution neuronal network or a recurrent neuronal network.

[0099] In another example, the pilot tone system is used with one or more additional motion detection system such as an optical camera, a radar, or ultrasonic acoustic detection.

[0100] FIG. 5 illustrates an example of multi-channel pilot tone data 500. The pilot tone data 500 shown shows a number of plots of individual pilot tone signals that were measured. Cardiac signals and breathing motion are well detected, but strongly depends on individual antenna channel.

[0101] In examples, Local antennas (at least one receive coil 116) receive the narrow band signals (pilot tone signals). Each antenna feeds a preamplifier an individual software defined receiver. Complex signals are processed and the motion appears differently in the individual signals as changes in magnitude or phase. The data is further processed and the 3D/4D information is translated into motion parameters.

[0102] The data (pilot tone data) can also feed a convolution neuronal network or a recurrent neuronal network. A recurrent neural network (RNN) is a class of artificial neural network where connections between nodes form a directed graph along a sequence. This allows it to exhibit dynamic temporal behavior for a time sequence. Unlike feedforward neural networks, RNNs can use their internal state (memory) to process sequences of inputs (here different frequencies). This makes them applicable to tasks such as unsegmented, connected motion recognition or camera motion recognition.

[0103] FIG. 6 illustrates a functional diagram of an X-ray system 600. In this example the X-ray system 600 comprises a CT or X-ray tube 602. Adjacent to a head of the subject 102 are a number of pilot reference receivers or multiple receive channels 116. Further away from the subject 102 is a single pilot reference transmitter which is a single transmit channel 110 or at least one transmit coil 114. There may also be multiple transmit coils 114 also. There is a supplementary motion feedback monitor 604. The motion feedback monitor 604 may be used to display to the subject 102 the current motion state and may help the subject 102 remain still. The X-ray system comprises an RF and SDR transceiver and feedback control which comprises the pilot tone system 106. This pilot tone system provides data to a feedback patient monitor 606. The feedback patient monitor 606 provides the image which is rendered by the motion feedback monitor 604. The pilot tone system 106 also provides data to ECG triggering and breathing triggering 608. The pilot tone system 106 also provides information to the reconstruction algorithm 610. An artificial or machine learning module 612 may be used for aiding during the reconstruction 610 as well as be trained with the data that is received via the pilot tone system 106.

[0104] FIG. 7 illustrates examples of a motion state 140 which can be derived from multi-channel pilot tone data 500. FIG. 7 shows several position measurements that were used with multi-channel pilot tone data 500. In the examples illustrated in FIG. 7 a simple model was used to determine the distance of a subject's head from multiple receive coils 116. Plot 700 shows the position of a subject's head using this model. Plot 702 shows the direction of the subject's nose from the data in plot 700. Likewise plot 700′ also shows a head position as measured using multiple receive coils. Plot 702′ shows a change in the subject's nose orientation.

[0105] FIG. 7 illustrates a simple example of how a set of pilot tone transmitters and receivers can be used to detect motion of the head. The images 702 and 702′ show a very simple head model in form of the vector pointing form the back of the head to the tip of the nose in the real coordinate system. The origin of the coordinate system denotes the isocenter of the CT scanner. The back of the head is assumed to be fix to the patient table and cannot move.

[0106] The images 700 and 700′ show a wire frame model of a 15-node pilot tone system. The positions of the nodes were derived from the spatial distribution of the pilot tone transmitters and receivers around the subject's head.

[0107] The coordinate system in these images is zeroed once the patient is placed on the patient table. Any movement will now affect the signal strength and phase among the different pilot tone transmitters and receivers. In the given model, a signal increase is mapped to the wire frame model by increasing the distance of the corresponding wire frame node from the (virtual) origin.

[0108] As a result, the wire frame gets distorted. The kind of distortion is characteristic for the head movement, e.g. shaking the head will lead to a signal increase for certain pilot tone transmitters and receiver combinations while others encounter a decrease. This insight was used for the simplified head model. The position of the nose tip is calculated by the spatially weighted average of the signals of the 15 pilot tone nodes. In the given example the volunteer turned his head from middle position (700, 702) to the right (negative y). In the wire frame model (700′, 702′), this this resulted in a tilt-like distortion. Accordingly, the head vector model moves its tip to negative y.

[0109] FIG. 8 illustrates an example of a magnetic resonance imaging system 800. Reference numerals reused in this figure indicate features or components which are equivalent to previously described features or components. Previously described components may not necessarily be described again.

[0110] The magnetic resonance imaging system 800 comprises a magnet 804. The magnet 804 is a superconducting cylindrical type magnet with a bore 806 through it. The use of different types of magnets is also possible; for instance it is also possible to use both a split cylindrical magnet and a so called open magnet. A split cylindrical magnet is similar to a standard cylindrical magnet, except that the cryostat has been split into two sections to allow access to the iso-plane of the magnet, such magnets may for instance be used in conjunction with charged particle beam therapy. An open magnet has two magnet sections, one above the other with a space in-between that is large enough to receive a subject: the arrangement of the two sections area similar to that of a Helmholtz coil. Open magnets are popular, because the subject is less confined. Inside the cryostat of the cylindrical magnet there is a collection of superconducting coils.

[0111] Within the bore 806 of the cylindrical magnet 804 there is an imaging zone 808 where the magnetic field is strong and uniform enough to perform magnetic resonance imaging. A region of interest 809 is shown within the imaging zone 808. The magnetic resonance data that is acquired typically acquired for the region of interest. A subject 102 is shown as being supported by a subject support 104 such that at least a portion of the subject 102 is at least partially within the imaging zone 808 and the region of interest 809.

[0112] Within the bore 806 of the magnet there is also a set of magnetic field gradient coils 810 which is used for acquisition of preliminary magnetic resonance data to spatially encode magnetic spins within the imaging zone 808 of the magnet 804. The magnetic field gradient coils 810 connected to a magnetic field gradient coil power supply 812. The magnetic field gradient coils 810 are intended to be representative. Typically magnetic field gradient coils 810 contain three separate sets of coils for spatially encoding in three orthogonal spatial directions. A magnetic field gradient power supply supplies current to the magnetic field gradient coils. The current supplied to the magnetic field gradient coils 810 is controlled as a function of time and may be ramped or pulsed.

[0113] Within the bore 806 of the magnet 804 is a magnetic resonance imaging antenna 814. The magnetic resonance imaging antenna 814 is shown as comprising the multiple transmit coils 114 and the multiple receive coils 116. The magnetic resonance imaging antenna 814 also comprises a number of radio-frequency coils 816 which are used for performing the magnetic resonance imaging. The radio-frequency system 108 is also connected to the radio-frequency coil 816. The arrangement shown in FIG. 8 enables the acquisition of magnetic resonance imaging data simultaneous with the use of the pilot tone system. In other examples the radio-frequency coils 816 may also function as the multiple transceiver coils 114 and/or multiple receive coils 116.

[0114] The radio frequency coils 816 may also be referred to as a channel or antenna. The magnetic resonance antenna 814 is connected to a radio frequency system 108. The magnetic resonance antenna 814 and radio frequency system 108 may be replaced by separate transmit and receive coils and a separate transmitter and receiver. It is understood that the magnetic resonance antenna 814 and the radio frequency system 108 are representative. The magnetic resonance antenna 814 is intended to also represent a dedicated transmit antenna and a dedicated receive antenna. Likewise the system 816 may also represent a separate transmitter and receivers. The magnetic resonance antenna 814 may also have multiple receive/transmit elements and the radio frequency system 108 may have multiple receive/transmit channels. For example if a parallel imaging technique such as SENSE is performed, the radio-frequency system 108 could have multiple coil elements.

[0115] The radio frequency system 816 and the gradient controller 812 are shown as being connected to the hardware interface 124 of the computer system 128.

[0116] The memory 128 is shown as containing machine executable instructions 820. The machine executable instructions 820 enable the processor to control the magnetic resonance imaging system 800 as well as perform various data processing and image processing tasks. The memory 128 is further shown as containing pulse sequence commands 830 instead of control commands. The pulse sequence commands 830 are commands or data which may be converted into such commands which are used for controlling the operation of the magnetic resonance imaging system 800. The memory 128 is further shown as containing magnetic resonance imaging data 832 that was acquired by controlling the magnetic resonance imaging system with the pulse sequence commands 830.

[0117] The memory 128 is further shown as containing a magnetic resonance image 834 that was reconstructed from the magnetic resonance imaging data 832. The motion state 140 may be used in different ways. For example, the motion state 140 may be used for gating the acquisition of the magnetic resonance imaging data 832 as well as being used in the reconstruction of the magnetic resonance image 834.

[0118] The memory 128 may further contains a time-dependent gradient pulse frequency 836 that was determined from the pulse sequence commands 830. The motion state 140 may be compared with the time-dependent gradient pulse frequency 836 to determine if there is peripheral nerve stimulation in the subject 102. If the motion state correlates above a certain degree or above a certain amplitude within the same frequency range as motion detected, there may be a peripheral nerve stimulation warning signal 838 that is generated.

[0119] FIG. 9 shows a flowchart which illustrates a method of operating the magnetic resonance imaging system 800 of FIG. 8. First in step 900 the magnetic resonance imaging system 800 is controlled with the pulse sequence commands 832 to acquire the magnetic resonance imaging data 834. As step 900 is performed steps 902, 904, and 906 are also performed.

[0120] Next in step 902, the at least one pilot tone signals 136 are transmitted by controlling at least a portion of the multiple transmit channels 110. Next in step 904, the pilot tone data 138 is acquired by controlling the at least one receive channel 112.

[0121] Then in step 906, the motion state 140 of the subject 102 is determined using the pilot tone data 138. This could for example be performed using a recurrent neural network. In a recurrent neural network both the pilot tone data 138 and the pilot tone signals 136 could be input. In other cases, the motion state 140 can be determined from the multi-channel pilot tone data 138 alone. For example, the periodic breathing or heart motion of a subject 102 may cause the pilot tone data 138 to have a frequency component which is equal to or about equal to the heart rate and/or breathing rate. The heart and/or breathing motion may therefore be determined by the pilot tone data 138 alone.

[0122] In step 908, the time-dependent gradient pulse frequency 810 is determined using the pulse sequence commands 830. Next in step 910 subject motion with a periodicity within a predetermined range or correlation of the time-dependent gradient pulse frequency is detected using the motion state 140. For example, the motion state can be compared to the time-dependent gradient pulse frequency 810 or there can for example be a correlation that is calculated on the fly. Finally, in step 912 the peripheral nerve stimulation warning signal 812 is generated if the subject motion is detected.

[0123] Another application is the detection of Peripheral Nerve Stimulation during magnetic resonance imaging. It is possible to use the pilot tone signals acquired by the receive coil array and correlate it with gradient waveform signal to detect and trigger for PNS detection. The full matrix of the receive coil is measured and correlated with the gradient waveform to detect PNS.

[0124] If certain thresholds are reached, the MR sequence is adapted to reduce PNS. The sequence automatically adapts for patient comfortable parameters. Measure: change readout direction, change sequence, gradient strength, reposition patient. The data (multi-channel pilot tone data) can also feed a convolution neuronal network or a recurrent neuronal network.

[0125] Strong gradients applied during MRI exams can trigger peripheral nerve stimulation resulting in motion of muscle fibers or whole muscles.

The PNS

[0126] Is discomfort for patient

[0127] level is individual for patient

[0128] Limits are set globally, disregarding individual sensitivity for PNS

[0129] Cannot be communicated by Patients with handicap or sedation. There is no quantitative feedback for operator,

[0130] cannot be detected by camera-based methods

[0131] Can induce MR artefact due to motion

[0132] Can lead to an unintended scan about, when the patient calls the operators due

[0133] PNS may be detected by using the pilot tone signals acquired by the receive coil array for PNS detection.

[0134] In general, PNS induced effects on the Pilot tone signals are expected to be lower than that of e.g. breathing. Due to this, and to distinguish from other motion the Pilot tone signals acquired by the receive coil may be correlated with the gradient waveform.

[0135] If certain thresholds are reached, the MR sequence is adapted to reduce PNS. The sequence automatically adapts for patient comfortable parameters. Possible measures are to change

[0136] change readout direction,

[0137] change sequence,

[0138] gradient strength,

[0139] position/pose of patient

[0140] Additional supplementary data may also be used such as optical, camera, radar, and ultrasonic acoustic detection.

[0141] Current MRI scanners feature a low-power transmit path independent from the transmit chain of the body coil for calibration purposes. Here, a small off-resonant coil is attached to the RF screen to the body coil. The transmit power for this coil was adjusted so that RF signals are in the same order of that originating from the spin system. Standard MRI coils are used for reception.

[0142] Pilot tone measurements can be interleaved or merged with the MR sequence. Tests showed that this setup allows to detect motion induced by breathing. Further tests were performed to increase the sensitivity of the set-up.

[0143] The FIG. 5 above shows an example of pilot tone magnitude signals. Additional information can be gained when simultaneously observing the phase of the acquired signals. The ideal position of the off-resonant coil was determined in tests to provide most sensitive outcome for breathing and heart motion. In the given experiments, the best setup was to place the coil on top of the patient's sternum. The acquisition of the pilot tone using all available RX coils allows for (limited) spatial sensitivity. This insight can be used to distinguish different motion types.

[0144] It is likely that for PNS detection another position is more suitable, e.g., close to the long muscles of the patients back.

[0145] The data (multi-channel pilot tone data) can also feed a convolution neuronal network or a recurrent neuronal network. A recurrent neural network (RNN) is a class of artificial neural network where connections between nodes form a directed graph along a sequence. This allows it to exhibit dynamic temporal behavior for a time sequence. Unlike feedforward neural networks, RNNs can use their internal state (memory) to process sequences of inputs (here different frequencies). This makes them applicable to tasks such as unsegmented, connected motion recognition or camera motion recognition (see FIG. 13 below).

[0146] FIG. 10 illustrates a software algorithm and functional building blocks of a system that may for example be incorporated into a magnetic resonance imaging system such as the medical system 800 illustrated in FIG. 8. Block 1000 represents the pilot tone system and the radio-frequency reference coil array. Block 1002 represents the gradient waveform from the pulse sequence commands. Block 1004 represents a software component that is a peripheral nerve stimulation detector and/or correlator 1004. The detector or correlator 1004 is able to take information about the gradient waveform 1002 and information from the pilot tone data 1000 to detect if there is peripheral nerve stimulation. This is then fed into the controller 1006.

[0147] For example, the controller 1006 may be equivalent to the processor 122. This information could then be forwarded or processed from the controller and fed to a neural network 1008 that may for example be equivalent to a neural network. The controller 1006 can use a detection of the peripheral nerve stimulation for example to modify behavior of the gradient amplifier 1010, and possibly even modify the behavior or change the pulse sequence commands 832. This data may also be provided to a peripheral nerve stimulation monitor 1014. This for example may be provided via the user interface 126.

[0148] The following scheme illustrated in FIG. 10 shows how the Pilot Tone data may be processed and used. [0149] In a first step the Pilot Tone data is correlated with the gradient waveforms. Depending on the level of signal correlation the controller decides: correlation below first threshold=no low PNS: run the sequence as planned [0150] correlation below second threshold=considerable PNS: adapt sequence [0151] correlation above second threshold=PNS at pain limit or considerable image artefacts expected: terminate scan by gradient amplifier interlock

[0152] 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.

[0153] Other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims. In the claims, the word “comprising” does not exclude other elements or steps, and the indefinite article “a” or “an” does not exclude a plurality. A single processor or other unit may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measured cannot be used to advantage. A computer program may be stored/distributed on a suitable medium, such as an optical storage medium or a solid-state medium supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems. Any reference signs in the claims should not be construed as limiting the scope.

[0154] 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.

[0155] Other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims. In the claims, the word “comprising” does not exclude other elements or steps, and the indefinite article “a” or “an” does not exclude a plurality. A single processor or other unit may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measured cannot be used to advantage. A computer program may be stored/distributed on a suitable medium, such as an optical storage medium or a solid-state medium supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems. Any reference signs in the claims should not be construed as limiting the scope.

LIST OF REFERENCE NUMERALS

[0156] 100 X-ray system [0157] 101 Computer Tomography Gantry [0158] 102 subject [0159] 103 bore [0160] 104 subject support [0161] 105 imaging zone [0162] 106 pilot tone system [0163] 108 radio frequency system [0164] 110 at least one transmit channel [0165] 112 at least one receive channel [0166] 114 at least one transmit coil [0167] 116 at least one receive coil [0168] 120 computer [0169] 122 processor [0170] 124 hardware interface [0171] 126 user interface [0172] 128 memory [0173] 130 machine executable instructions [0174] 132 control commands [0175] 134 medical imaging data [0176] 136 pilot tone signal [0177] 138 pilot tone data [0178] 140 motion state [0179] 142 motion state model [0180] 144 medical image [0181] 200 control the X-ray system to acquire the medical imaging data during acquisition of the pilot tone data [0182] 202 transmit the at least one pilot tone signal by controlling the at least one transmit channel [0183] 204 acquire the pilot tone data by controlling the at least one receive channel [0184] 206 determine a motion state of the subject using the pilot tone data [0185] 300 reconstruct a tomographic medical image using the medical imaging data [0186] 302 correct the reconstruction of the tomographic medical image using the motion state of the subject [0187] 400 gate acquisition of the medical imaging data using the motion state of the subject or modify acquisition of the medical imaging data using the motion state of the subject [0188] 500 multi-channel pilot tone data [0189] 600 X-ray system [0190] 602 CT or X-ray tube [0191] 604 motion feedback monitor [0192] 606 feedback patient monitor [0193] 608 ECG triggering and breating [0194] 610 reconstruction including pilot data [0195] 612 AI-machine learning module [0196] 700 head position [0197] 700′ head position [0198] 702 nose position [0199] 702′ nose position [0200] 800 magnetic resonance imaging system [0201] 804 magnet [0202] 806 bore of magnet [0203] 808 imaging zone [0204] 809 region of interest [0205] 810 magnetic field gradient coils [0206] 812 magnetic field gradient coil power supply [0207] 814 magnetic resonance antenna [0208] 816 radio-frequency coil [0209] 830 pulse sequence commands [0210] 832 magnetic resonance imaging data [0211] 834 magnetic resonance image [0212] 836 time dependent gradient pulse frequency [0213] 838 peripheral nerve stimulation warning signal [0214] 900 acquire magnetic resonance imaging data [0215] 902 transmit at least one pilot tone signal by controlling at least a portion of the multiple transmit channels to transmit the at least one pilot tone signal [0216] 904 acquire pilot tone data by controlling at least a portion of the multiple receive channels to receive the pilot tone data [0217] 906 determine a motion state of the subject using the pilot tone data [0218] 908 determine a current gradient pulse frequency using the pulse sequence commands [0219] 910 detect subject motion with a periodicity within a predetermined range of the current gradient pulse frequency using the pilot tone data [0220] 912 provide a peripheral nerve stimulation warning signal if the subject motion is detected [0221] 1000 Pilot/RF reference Coil Array [0222] 1002 Gradient Waveform [0223] 1004 PNS Detector/Correlator [0224] 1006 Controller [0225] 1008 Neuronal Network [0226] 1010 Gradient Amplifier [0227] 1014 PNS monitor