Systems and methods for monitoring and suppressing radio frequency (RF) noise

Abstract

Radio frequency (RF) noise should be suppressed and / or avoided in the environment of the medical imaging or treatment system 1. This is achieved by a system for monitoring radio frequency (RF) noise and a computer-implemented method for suppressing and / or avoiding radio frequency (RF) noise. The medical imaging or treatment system 1 is arranged inside an operating room 2, and the monitoring system has a plurality of sensors 4, 5, 7, configured for continuous wideband detection of radio frequency (RF) signals, a first sensor 4 is arranged inside the operating room 2 and a second sensor 5 is arranged outside the operating room 2, and the sensors 4, 5, 7 are configured to provide sensor data, and the monitoring system further has a processor unit 8, the sensors 4, 5, 7 are connected to the processor unit 8, the processor unit has at least one memory 9 that stores instructions and at least one processor 10, and the at least one processor executes the instructions to perform the steps of calculating a noise level and spectrum based on the sensor data in the processor unit 8, and performing a procedure to suppress and / or avoid RF noise and spurious signals based on the noise level.

Description

[Technical Field]

[0001] The present invention relates to the field of monitoring radio frequency (RF) noise in the environment of a medical imaging or therapy system. The present invention further relates to a method for suppressing and / or avoiding radio frequency (RF) noise in the environment of a medical imaging or therapy system. [Background technology]

[0002] In the field of medical imaging or therapy systems, a good diagnostic experience is essential along with good image quality. Medical imaging or therapy systems will become increasingly autonomous as they become less dependent on on-site operator activity and as workflow steps are automated and remotely controlled. Summary of the Invention [Problem to be solved by the invention]

[0003] Imaging or treatment guidance requires a seamless workflow. For this and other reasons, new features are introduced and used near medical imaging or treatment systems. For example, compatibility of multiple devices with regard to image quality is crucial. External and additional devices, such as portable monitoring devices, vital sign sensors, and mobile anesthesia systems, are controlled by local hospital services and clinical operators. This additional equipment is placed, for example, in the operating room of the medical imaging or treatment system and connected to the AC supply channel and local communication channel. Positioning and placement are often performed with regard to clinical requirements and constraints, such as limited space and accessibility. Signal integrity has not been able to be controlled to date. For example, reports from MRI sites indicate image quality issues caused by spurious signal injection of digital noise in the MRI image band. Spurious signals from digital components, such as local switching step-up converters, are unstable in terms of frequency, amplitude, and phase and are often correlated with the device's operating mode, positioning, and orientation.

[0004] It is an object of the present invention to provide a system and method for monitoring radio frequency (RF) noise in the environment of a medical imaging or treatment system in order to suppress and / or avoid RF noise. [Means for solving the problem]

[0005] According to the present invention, this object is addressed by the subject matter of the independent claims. Preferred embodiments of the invention are set forth in the dependent claims.

[0006] Therefore, according to the present invention, a system for monitoring radio frequency (RF) noise in the environment of a medical imaging or treatment system is contemplated, the medical imaging or treatment system being arranged in an operating room, the system having a plurality of sensors configured for continuous broadband detection of radio frequency (RF) signals, a first set of sensors being arranged inside the operating room and a second set of sensors being arranged outside the operating room, the sensors being configured to provide sensor data, the system further having a processor unit, the sensors being connected to the processor unit, the processor unit having at least one memory for storing instructions and at least one processor, the at least one processor executing the instructions to calculate a noise level and spectrum based on the sensor data in the processor unit, and to perform a procedure for suppressing and / or avoiding RF noise and spurious signals based on the noise level. In this application, an operating room is understood to be a room shielded from the outside by an RF cage. This distinguishes between the terms "inside" and "outside," i.e., they are defined by an RF-shielded cabin and the unshielded outside world where all kinds of RF radiation are present. Continuous wideband sampling contrasts with known intermittent sampling in the Larmor frequency band. In particular, continuous wideband sampling of RF signals is guaranteed to be at least wider than the MR bandwidth. RF noise and spurious signals are generally signals in the RF spectrum that can adversely affect the function of a medical imaging or therapy system.

[0007] The very wideband sampling of the RF signal achieves capturing RF signals that exceed the typical bandwidth of imaging data (e.g., magnetic resonance signals) acquired by medical imaging or therapy systems. The data compression module on board the sensor assembly enables efficient transfer of the acquired data in that transmission of the vast amount of uncompressed data output by the sensor is avoided.

[0008] In a technically advantageous embodiment of the system, at least one processor is configured to execute a machine learning algorithm. Machine learning can include neural networks, autoencoders, decision trees, support vector machines, and other types of machine learning. Neural networks and other machine learning techniques have various advantages and applications, but their most common advantage is their utility for classification and clustering. Such machine learning models are learned (or trained) by processed examples, each containing a known "input" and "outcome," and form a probability-weighted association between the two, which is stored within the model's own data structure. Training from a given example is typically performed by determining the difference between the model's processed output (often a prediction) and a target output. Learning is the adaptation of a machine learning model to better handle a task by taking sample observations into account. Learning involves adjusting the model's parameters to improve the accuracy of the results. This is done by minimizing the observed error. Learning is complete when examining additional observations does not effectively reduce the error rate.

[0009] The machine learning algorithm is trained to return characterizations of (future) hardware failures and / or artifact-causing operations of a medical imaging or therapy system. The returned characteristics can be used to control the settings of an imaging sequence to reduce sensitivity to the characterized (possible) hardware failures or artifact-causing operations. For example, the settings can be adapted to move expected image artifacts outside the field of view of images resulting from the imaging sequence. Furthermore, artifact-causing operations or hardware failures can be caused by RF-active items or metal devices accidentally present in or near the examination area. The artifact-causing operations can cause image artifacts in the control of the medical imaging or therapy system, adversely affecting image quality, treatment effectiveness, or accuracy.

[0010] The present invention achieves an automatic assessment of acquired very wideband RF signals regarding the technical state of a medical imaging or therapy system, in particular whether the medical imaging or therapy system is in a suitable and safe state to perform a planned imaging or therapy protocol. The assessment of the present invention may also be performed during installation of the medical imaging or therapy system.

[0011] The very broad spectrum of the sensor assembly can be divided over several narrower ranges, which can be selected by switchable filter bands.

[0012] In another technically advantageous embodiment of the system, at least one of the sensors is a portable sensor device for measuring RF signals on the spot, which has the advantage that it can be used to perform measurements in particularly critical locations.

[0013] In technically advantageous embodiments of the system, the sensor is coupled to the processor unit via a non-galvanic signal path. In particular, in technically advantageous embodiments of the system, the sensor is connected to the processor unit via an optical and / or shielded wire-based and / or wireless signal path. This has the advantage that a non-galvanic signal path prevents common-mode coupling.

[0014] In a technically advantageous embodiment of the system, the sensor has a dual mode antenna for WLAN control and RF signal detection, and / or the sensor has separate antennas using a diplexer for WLAN control and RF signal detection. The antennas can be realized, configured, and mixed for sensitivity to the electromagnetic field components E and H.

[0015] In another technically advantageous embodiment of the system, the medical imaging or therapy system is a magnetic resonance imaging (MRI) system and the sensor is time-synchronized with an MRI multi-receiver channel of the MRI system.

[0016] In a technically advantageous embodiment of the system, the medical imaging or treatment system is a magnetic resonance imaging (MRI) system, and at least one sensor for detecting radio frequency (RF) signals is disposed around the MRI system. The sensor disposed around the MRI system can be used to calculate the RF noise field within the MRI system. Before the start of a scan, the RF noise spectrum within the MRI system arising from noise sources external to the scanner (e.g., surrounding equipment) can be measured and used as an estimate of the baseline noise floor. During the scan, the magnetic field outside the scanner is monitored by the sensor, and RF noise within the scanner can be retroactively removed from the acquired k-space signal based on real-time measurements and pre-scan calibration.

[0017] Another aspect of the present invention contemplates a medical imaging or therapy system having a system for monitoring radio frequency (RF) operation of the magnetic resonance imaging system described above.

[0018] In another aspect of the invention, the object is achieved by a computer-implemented method for suppressing and / or avoiding radio frequency (RF) noise in an environment of a medical imaging or therapy system by a system that monitors radio frequency (RF) noise in the environment of the medical imaging or therapy system, the medical imaging or therapy system being located in an operating room, the system having a plurality of sensors, the plurality of sensors being configured for detecting radio frequency (RF) signals, a first sensor being located in the operating room and a second sensor being located outside the operating room, the plurality of sensors being configured to provide sensor data, the system further having a processor unit, the processor unit having at least one memory for storing instructions and at least one processor for executing the instructions, the method comprising the steps of measuring RF signals by the sensors inside the operating room and outside the operating room and providing sensor data, calculating a noise level in the processor unit based on the sensor data, and executing a procedure for suppressing and / or avoiding RF noise based on the noise level.

[0019] The term medical imaging or therapy system can be used to refer to different systems such as magnetic resonance imaging (MRI) systems, X-ray systems, computed tomography (CT) systems, or therapy systems such as linear accelerator-based therapy systems or proton therapy systems.

[0020] In a technically advantageous embodiment of the method, the step of performing the procedure based on the noise level is based on a thresholding technique with adaptive window selection, the advantage of which is its effectiveness in providing an appropriate procedure.

[0021] In another technically advantageous embodiment of the method, performing the procedure for suppressing and / or avoiding RF noise based on the noise level includes modifying the operation of a component of the medical imaging or therapy system based on the noise level, whereby, to the extent that the noise is correlated with the operating mode, the change in operation of the component of the medical imaging or therapy system can result in an improvement in the noise level.

[0022] In a technically advantageous embodiment of the method, measuring the RF signals with sensors and providing sensor data includes sampling signals from sensors within the operating room and from sensors outside the operating room, and processing the sensor data in the processor unit includes subtracting or dividing the sensor data from within the operating room and from outside the operating room to calculate corresponding noise levels.

[0023] In another technically advantageous embodiment of the method, the at least one processor is configured to execute a neural network machine learning algorithm, and processing the sensor data in the processor unit comprises feeding the sensor data to the neural network machine learning algorithm, and the neural network machine learning algorithm is trained to identify devices by the fingerprints of their spurious signal bands.

[0024] In a technically advantageous embodiment of the method, the step of performing the procedure based on the noise level comprises suggesting to the operator an adapted operating mode for the medical imaging system to achieve a clinical image with better image quality.

[0025] In another technically advantageous embodiment of the method, the medical imaging or treatment system is a magnetic resonance imaging (MRI) system, the sensors inside and outside the operating room are time-synchronized with an MRI digital multi-receiver of the MRI system, and the step of performing the procedure based on the noise level includes removing noise as much as possible from the clinical image in k-space or image space. In one embodiment of the present invention, the noise is removed with the help of a trained machine learning model. In cases with strong signals (MRI received signals exceeding the dynamic range), machine learning can help estimate the true signal level without additional RF noise.

[0026] These and other aspects of the invention will be apparent from and elucidated with reference to the embodiments described hereinafter, but such embodiments do not necessarily represent the full scope of the invention, and reference should therefore be made to the claims and this specification for interpreting the scope of the invention. [Brief explanation of the drawings]

[0027] [Figure 1] 1 is a diagram that illustrates a schematic of a system for monitoring radio frequency (RF) noise in the environment of a medical imaging or therapy system, in accordance with an embodiment of the present invention; [Figure 2] 1 is a flowchart of a computer-implemented method for suppressing and / or avoiding radio frequency (RF) noise in the environment of a medical imaging or therapy system, according to one embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0028] FIG. 1 shows a schematic diagram of a system for monitoring radio frequency (RF) noise in the environment of a medical imaging or treatment system 1, according to an embodiment of the present invention.

[0029] FIG. 1 shows a medical imaging or treatment system 1 located inside an operating room 2, which can be accessed through a door 3 shown in FIG. 1. The medical imaging or treatment system 1 can be, for example, a magnetic resonance imaging (MRI) system, an X-ray system, a computed tomography (CT) system, or a treatment system such as a linear accelerator-based treatment system or a proton therapy system. Another application field of the present invention is for interventional radiology suites, where biopsies, diagnoses, or treatments are precisely guided by real-time fluoroscopy and / or MRI. Here, many individual devices are located inside the operating room 2, and signal integrity is crucial for patient safety. The operating room is understood to be a room shielded from the outside by an RF cage. This distinguishes the terms "inside" and "outside," which are defined by the RF-shielded cabin and the unshielded outside world with all kinds of RF radiation.

[0030] The system for monitoring radio frequency (RF) noise includes multiple sensors 4, 5, and 7, each configured to detect a radio frequency (RF) signal. A first sensor 4 is located inside the operating room 2, and a second sensor 5 is located outside the operating room 2. The sensors 4, 5, and 7 are configured to provide sensor data. Specifically, the sensors may be wideband sensors for measuring RF noise. In particular, the wideband sampling of the RF signal is continuous, and in one embodiment, the sampling is at least wider than the MR bandwidth. The continuous wideband sampling contrasts with known intermittent sampling in the Larmor frequency band. The sensors 4, 5, and 7 are connected to a processor unit 8, which includes a memory 9 for storing instructions and a processor 10 for executing instructions. The sensors may be coupled to the processor unit 8, for example, via a non-galvanic signal path 6. In one embodiment, an optical and / or wireless signal path 6 may be used. In one embodiment, continuous wideband sampling is contemplated, where the sampling is at least wider than the MR bandwidth of the RF signal. Sensor data from a sensor 4 located inside the operating room 2 can be compared with sensor data from a second sensor 5 located outside the operating room 2 to monitor the integrity of the RF cage. As a result, predictive maintenance can be required.

[0031] The processor unit 8 can function as a sensor hub where the sensor signal paths 6 converge. For this purpose, the processor unit 8 can further include a software-defined radio (SDR), allowing the sensors 4, 5, and 7 to be remotely controlled and configured. The processor 10 can, for example, be a field-programmable gate array (FPGA) that can be loaded with logic circuits adapted for evaluation. In particular, the processor 10 can be configured to execute neural network machine learning algorithms, which can perform analysis of individual noise and signal sources. For this purpose, the neural network is pre-trained accordingly. The neural network determines information flows for, for example, remote operators and system operators for predictive maintenance. The trained network identifies devices by fingerprinting spurious signal bands. Furthermore, the signals of the sensors 4, 5, and 7 can be digitized by the processor unit 10. For this purpose, the processor unit 10 includes corresponding devices, such as ADC converters. The digitized data and preselected information are transferred, collected, and stored in the collection module 11. To avoid huge amounts of data due to continuous wideband sampling, it is advantageous to have local data processing before submitting the data remotely. The collection module 11 can be connected to the processor unit 8 as a standalone module, but can also be integrated into the processor unit 8. For example, it can be a cloud-based collection module 11 for storing data outside the system. The collection module 11 can be connected to a service module 12, for example, for the purposes of service coordination and fault prediction. Furthermore, the service module 12 can provide other customer guidance functions included in an app or can display guidance data on an output unit such as a monitor.

[0032] The sensors 4, 5, and 7 are equipped with separate antennas, either dual-mode antennas or diplexers for WLAN control and separate MR-band antennas. The antennas can be realized, configured, and mixed based on their sensitivity to the E and H electromagnetic field components. In one embodiment, signals from the internal sensor 4 and the external sensor 5 of the operating room 2 are narrowband sampled and subtracted or divided in the MRI channel. The signals are monitored over time, and significant changes and signal events are addressed with timestamps and stored, for example, in the acquisition module 11. The events are then reported, for example, by an output unit in the service module 12. This reduces the amount of data to a reasonable amount. Measurements within the operating room 2 help localize problems and classify them into categories such as "internal noise source," "broken RF cage" or "broken RF door," and "external noise source." Defined threshold warnings inform service and operators about image quality. In yet another embodiment, based on noise level analysis, more robust MRI sequences are suggested to the operator to achieve clinical images with acceptable image quality.

[0033] In addition, the sensors 4, 5, 7 may be partly portable sensor devices. Here, the portable sensor devices may be placed in a wall holder 13. For analysis, the portable sensor devices may be removed from the wall holder 13 and moved within the environment of the medical imaging or treatment system 1 in order to analyze noise sources in situ. To enable this, the portable sensor devices are optionally configured to be battery powered and configured to transmit data, for example wirelessly, to the wall holder 13. The wall holder 13 acts as a power source / charger and collects data wirelessly and transfers it to the processor unit 8.

[0034] When using a system to monitor radio frequency (RF) noise in the environment of an MRI system, sensors 4 and 5 inside and outside the operating room 2 are time synchronized with the MRI digital multi-receiver. Signals from sensors 4, 5, and 7 are fed to a processor unit 8 where a neural network machine learning algorithm is executed. The neural network machine learning algorithm is trained to remove noise from clinical images in k-space or image space to filter out cases that may have too strong signals, as spurious signals will saturate the MR RX chain and introduce nonlinearity.

[0035] In further embodiments, the signal chains of the sensors 4, 5, 7 can be switched between different modes. Here, for example, modes for narrowband or wideband signal detection can be provided. Also, for example, in the case of magnetic resonance imaging, different modes can be provided. These can be, for example, modes for MR imaging or service or device monitoring modes.

[0036] During installation of the medical imaging or therapy system 1, continuous monitoring of signal integrity can be provided by sensors 4, 5, and 7. Consequently, for example, a representation of signal and noise levels can be presented on a display unit, e.g., the monitor of 3D glasses. This guidance can provide transparency for on-site service during installation. This also facilitates the recognition of noise generated by external X-ray scanners and accessory equipment, e.g., anesthesia, monitors, surgical robots, etc., and their reduction through positioning and orientation guidance. Software subroutines, for example, communicate with the MRI system software and monitor noise analysis for the user and remote operator. Simultaneously, the operational phase of the MRI system adds data acquired from the noise sensors 4, 5, and 7.

[0037] In further embodiments, the sensor 7 can be placed directly around the MRI system, for example, attached to an external bore cover like a magnetic field camera. The sensor 7 around the MRI system can transmit in addition to receiving, or can be paired with a sensor around or inside the MRI system. This enables active noise cancellation during acquisition by transmitting a signal through the transmitter that cancels unwanted RF noise through destructive interference within the MRI system bore. For real-time processing of RF noise during a scan, high-speed processing hardware such as an FPGA can be used to determine the transmit fields required for active cancellation, with the field propagation equations from the sensors 4, 5, and 7 to the receive coils pre-programmed for efficient processing. Alternatively, instead of adding a transmitter dedicated to active noise cancellation, the RF pulses transmitted by the MRI system's main transmit coil can be designed to recognize RF noise and transmit a cancellation term to suppress RF noise at the receive coils during acquisition. For example, active sampling techniques with automated real-time sequence adjustment can be used. To calculate noise levels based on sensor data, Maxwell's equations can be used to calculate the RF noise field within the MRI system from sensors outside the MRI system.

[0038] Sensor data from the first sensor 4 in the operating room and sensors 7 placed directly around the MRI system 1 can generally be used in post-processing / reconstruction to correct the acquired MRI data, thereby achieving image noise reduction / enhancement. Sensor data from the sensor 7 and the MRI receive coils can be compared to assess the fidelity of the acquired MRI data (or data to be acquired in the planned sequence). If RF noise dominates the MRI signal, in embodiments of the present invention, the following measures can be implemented: estimate the effective SNR of the planned image, and / or warn the operator, and / or suggest an MRI sequence that is more robust with respect to noise (e.g., by more signal averaging).

[0039] Before a scan begins, the RF noise spectrum within the MRI system coming from sources external to the MRI system (e.g., peripheral devices) can be determined and used as a baseline noise floor estimate. During the scan, fields external to the MRI system are monitored by sensors 4, 5, and 7, and based on real-time measurements and pre-scan calibration, RF noise within the MRI system can be retroactively removed from the acquired k-space signals. In one embodiment, the additional RF noise from the acquired k-space data can be removed during post-processing.

[0040] 2 shows a flowchart of a computer-implemented method for suppressing and / or avoiding radio frequency (RF) noise in an environment of a medical imaging or therapy system according to one embodiment of the present invention. In step S1, a system for monitoring radio frequency (RF) noise in an environment of the medical imaging or therapy system 1 is provided. The medical imaging or therapy system 1 is disposed inside an operating room 2. The system includes a plurality of sensors 4, 5, 7, each configured for RF signal detection, a first sensor 4 located inside the operating room 2, and a second sensor 5 located outside the operating room 5, the sensors 4, 5, 7 configured to provide sensor data. The system further includes a processor unit 8, the sensors 4, 5, 7 connected to the processor unit 8. The processor unit 8 includes at least one memory 9 for storing instructions and at least one processor 10 for executing instructions. In step S2, RF signals are measured by the sensors 4, 5, 7 inside the operating room 2 and outside the operating room 2, and sensor data is provided. In step S3, a noise level and spectrum based on the sensor data are calculated in the processor unit 8. In one embodiment of the present invention, the processor 10 is configured to execute a neural network machine learning algorithm. Thus, the processing step of the sensor data in the processor unit 8 can include an additional step of feeding the sensor data to a neural network machine learning algorithm, which is trained to identify devices by the fingerprints of their spurious signal bands. In step S4, a procedure for suppressing and / or avoiding RF noise based on the noise level is executed. In one embodiment, to suppress and / or avoid RF noise, the operation of components of the medical imaging or therapy system 1 can be changed based on the noise level. In another embodiment, an adapted operating mode for the medical imaging system 1 is suggested to the operator to achieve clinical images with better image quality. Thus, the procedure for suppressing and / or avoiding RF noise includes guiding and warning the operator of the medical imaging or therapy system 1.This adds a layer of interaction with the operator of the medical imaging or therapy system 1 when a noise problem is detected. Only certain MRI sequences may be affected, or an increase in scan time can keep the scanner running until service arrives.

[0041] In one embodiment, real-time wideband signal and noise monitoring is used to contemplate control and guidance of clinical and interventional workflows based on continuous monitoring of RF noise inside and outside the operating room 2 of the medical imaging or treatment system 1. Additionally, threshold and window-based operations for predictive maintenance and customer guidance are provided. The local processor unit 8 includes, for example, FPGA analysis using machine learning algorithms to generate and prepare data for operator guidance and predictive maintenance. Thus, guidance and monitoring are provided to, among other things, help operators optimize equipment positioning and alignment to achieve the best signal integrity. This improves workflows for, for example, acquiring MR images.

[0042] In another embodiment, the sensors 4, 5, 7 inside and outside the operating room 2 are time synchronized with the MRI digital multi-receiver of the MRI system. Noise from the clinical images in k-space or image space is removed as much as possible using knowledge of the noise spectrum from the sensor signals from sensors 4 and 7 (in the operating room / RF cabin). This can be achieved, for example, by feeding the signals to a neural network machine learning algorithm running on a processing unit that removes noise from the clinical images in k-space or image space.

[0043] While the invention has been illustrated and described in detail in the drawings and the 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. 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. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage. Any reference signs in the claims are not to be construed as limiting the scope. Moreover, for the sake of clarity, not all elements in the drawings have been labeled with reference signs. [Explanation of symbols]

[0044] 1 Medical imaging or treatment systems 2 RF-shielded operating rooms 3-door 4 Sensors inside the operating room 5. Sensors outside the operating room 6 Signal Path 7 Sensors in Medical Imaging Systems 8 processor units 9. Memory 10 processors 11 Collection Module 12 Service Module 13 Wall Holder

Claims

1. 1. A system for monitoring radio frequency (RF) noise and spurious signals within an environment of a medical imaging or therapy system, the medical imaging or therapy system being located within an operating room, the system comprising: a sensor assembly including a plurality of sensors configured for continuous ultra-wideband detection of radio frequency (RF) signals having a bandwidth of at least 2 MHz, or 5 MHz, or 10 MHz, a first sensor located inside the operating room and a second sensor located outside the operating room, the sensors configured to provide sensor data, the sensor assembly having a data compression module for compression of the detected RF signals; a processor unit, the sensor being connected to the processor unit, the processor unit having at least one memory storing instructions including a machine learning algorithm and at least one processor; and wherein the processor executes the instructions to: calculating a noise level and spectrum based on sensor data in the processor unit; controlling a machine learning module to return characteristics of the likely malfunction or artifact-causing operation of the medical imaging or therapy system; executing a procedure for controlling the medical imaging or therapy system to avoid or reduce operations that cause the characterized faults or artifacts; To run the system.

2. 10. The system of claim 1, wherein the procedure for controlling the medical imaging or therapy system includes resetting one or more imaging sequences to reduce sensitivity to motion that imparts the characterized fault or artifact.

3. The system of claim 1 or 2, wherein at least one of the sensors is a portable sensor device for measuring RF signals in situ.

4. The system of claim 1 , wherein the sensor is coupled to the processor unit via a non-galvanic signal path.

5. The system of claim 4 , wherein the sensors are connected to the processor unit via optical and / or shielded wire-based and / or wireless signal paths.

6. 6. The system of claim 1, wherein the sensor has a dual-mode antenna for WLAN control and RF signal detection, and / or the sensor has separate antennas using a diplexer for WLAN control and RF signal detection.

7. 7. The system of claim 1, wherein the medical imaging or therapy system is a magnetic resonance imaging (MRI) system, and the sensor is time-synchronized with an MRI multi-receiver channel of the MRI system.

8. 8. The system of claim 1, wherein the medical imaging or therapy system is a magnetic resonance imaging (MRI) system and at least one sensor for detecting radio frequency (RF) signals is arranged around the MRI system.

9. A medical imaging or therapy system comprising a system for monitoring radio frequency (RF) operation of a magnetic resonance imaging system according to any one of claims 1 to 8.

10. 1. A computer-implemented method for suppressing and / or avoiding radio frequency (RF) noise in an environment of a medical imaging or therapy system by a system that monitors radio frequency (RF) noise in the environment of the medical imaging or therapy system, the medical imaging or therapy system being located in an operating room, the system comprising: a plurality of sensors configured for continuous broadband detection of radio frequency (RF) signals, a first sensor located inside the operating room and a second sensor located outside the operating room, the sensors configured to provide sensor data; a processor unit, the sensor being connected to the processor unit, the processor unit having at least one memory for storing instructions and at least one processor for executing the instructions; wherein the method comprises: measuring RF signals with the sensors inside the operating room and outside the operating room and providing sensor data; calculating a noise level in the processor unit based on the sensor data; performing a procedure for suppressing and / or avoiding RF noise based on the noise level; A method having the following.

11. 11. The method of claim 10, wherein performing the procedure for suppressing and / or avoiding RF noise based on the noise level comprises modifying operation of a component of the medical imaging or therapy system based on the noise level.

12. measuring RF signals with the sensors and providing the sensor data comprises sampling signals from the sensors inside the operating room and from the sensors outside the operating room; 12. The method of claim 10 or 11, wherein processing the sensor data in the processor unit comprises subtracting or dividing the sensor data from inside and outside the operating room to calculate a corresponding noise level.

13. the at least one processor is configured to execute a neural network machine learning algorithm; 13. The method of claim 10, wherein processing the sensor data in the processor unit comprises feeding the sensor data to the neural network machine learning algorithm, the neural network machine learning algorithm being trained to identify devices by the fingerprints of their spurious signal bands.

14. 14. The method of claim 10, wherein the step of performing the procedure based on the noise level comprises the step of suggesting to an operator an adapted operating mode for the medical imaging system to achieve a clinical image with better image quality.

15. 15. The method of claim 10, wherein the medical imaging or therapy system is a magnetic resonance imaging (MRI) system, the sensors inside and outside the operating room are time-synchronized with an MRI digital multi-receiver of the MRI system, and the step of performing the procedure based on the noise level comprises removing as much noise as possible from clinical images in k-space or image space.

Images