A control system for a magnetic resonance imaging system

Abstract

The application provides a control system of a magnetic resonance imaging system, which comprises: a vibration sensor for collecting a first vibration signal of a gradient coil of the magnetic resonance imaging system; a patient voice collection module for collecting an initial voice signal of a patient after a pre-stored signal reading delay time; a voice control device comprising a first signal processing module connected with the vibration sensor and the patient voice collection module respectively, for receiving and preprocessing the first vibration signal and the initial voice signal, performing amplitude correction on the preprocessed first vibration signal based on a pre-stored amplitude gain adjustment parameter, obtaining a second vibration signal, performing gradient noise elimination on the preprocessed initial voice signal based on the second vibration signal to obtain a target voice signal; a central control console connected with the first signal processing module, for obtaining the target voice signal and sending it to a first voice playing module; and the first voice playing module for playing the target voice signal.

Description

Technical Field

[0001] This application relates to the field of medical technology, and in particular to a control system for a magnetic resonance imaging system. Background Technology

[0002] Magnetic resonance imaging (MRI) is a medical imaging method based on the nuclear magnetic resonance phenomenon. It is one of the modern large-scale medical imaging diagnostic devices, characterized by no electromagnetic radiation, high contrast, multiple parameters, and imaging in any orientation. It has an increasingly wide range of applications in modern clinical medical diagnosis.

[0003] From the perspective of equipment layout, a magnetic resonance imaging system is divided into an operating room, a scanning room, and an equipment room. The equipment room is used to house electronic equipment such as scanning control units, radio frequency amplifiers, gradient cabinets, water-cooled cabinets, and power supplies. The scanning room is used to house equipment such as magnets, gradient coils, radio frequency coils, patient scanning beds, patient ventilation systems, and air conditioning units. The operating room is used to house devices for controlling various magnetic resonance equipment in the equipment room and the scanning room, as well as operating computers for scanning process control and image reconstruction.

[0004] In clinical diagnosis, operators in the scanning room not only need to constantly monitor the status of the scanning room, but also need to interact with patients in real time. For example, to ensure image quality, operators sometimes need to give commands to patients via voice to cooperate with the scanning; when patients feel uncomfortable and need to ask the operator for help, they also need to communicate with the operator via voice.

[0005] During a magnetic resonance imaging (MRI) scan, gradient pulses applied to the gradient coils between scans cause the coils to vibrate. This vibration generates audio noise, which introduces gradient noise interference into the speech exchange between the patient and the operator, captured by the microphone. In some cases, the speech exchange is even drowned out by the gradient noise, making it impossible for the patient and operator to communicate. Summary of the Invention

[0006] In view of this, this application provides a control system for a magnetic resonance imaging system, which solves the problem of gradient noise interference in the voice interaction between the patient and the operator in related technologies.

[0007] This application provides a control system for a magnetic resonance imaging (MRI) system, comprising: a vibration sensor for acquiring a first vibration signal from the gradient coil of the MRI system; a patient voice acquisition module for acquiring an initial voice signal from a patient after a pre-stored signal reading delay time; a voice control device including a first signal processing module connected to both the vibration sensor and the patient voice acquisition module, for receiving and preprocessing the first vibration signal and the initial voice signal, and for performing amplitude correction on the preprocessed first vibration signal based on pre-stored amplitude gain adjustment parameters to acquire a second vibration signal, and for performing gradient noise cancellation on the preprocessed initial voice signal based on the second vibration signal to obtain a target voice signal; a central control unit connected to the first signal processing module for acquiring the target voice signal and sending the target voice signal to a first voice playback module; and a first voice playback module connected to the central control unit for playing the target voice signal.

[0008] The control system of the magnetic resonance imaging system according to the embodiments of this application may also have the following additional technical features:

[0009] In the above technical solution, optionally, the first signal processing mold body is used to: multiply the preprocessed first vibration signal with the amplitude gain adjustment parameter to obtain the second vibration signal; and subtract the preprocessed initial speech signal from the second vibration signal to obtain the target speech signal.

[0010] In any of the above technical solutions, optionally, the first signal processing module is further configured to: acquire audio noise from the patient's voice acquisition module and a third vibration signal acquired by the vibration sensor when debugging or calibrating the magnetic resonance imaging system; acquire an amplitude gain adjustment parameter and a signal reading delay time based on the audio noise and the third vibration signal; the amplitude gain adjustment parameter is the ratio of the maximum amplitude of the preprocessed audio noise to the maximum amplitude of the preprocessed third vibration signal; and the signal reading delay time is the difference between the occurrence time of the maximum amplitude of the preprocessed audio noise and the occurrence time of the maximum amplitude of the preprocessed third vibration signal.

[0011] In the above technical solution, optionally, the patient voice acquisition module is disposed on the magnet housing and located at the port position of the scanning cavity enclosed by the magnet housing; the vibration sensor is disposed on the gradient coil inside the magnet housing.

[0012] In the above technical solution, optionally, the first signal processing module includes: a first signal conditioning module connected to the patient speech acquisition module, used for low-pass filtering and amplification of the initial audio signal; a first analog-to-digital converter connected to the first signal conditioning module, used for analog-to-digital conversion of the amplified initial speech signal to generate a pre-processed initial speech signal; a second signal conditioning module connected to the vibration sensor, used for low-pass filtering and amplification of the first vibration signal; a second analog-to-digital converter connected to the second signal conditioning module, used for analog-to-digital conversion of the amplified first vibration signal to generate a pre-processed first vibration signal; and a noise reduction module connected to the first and second analog-to-digital converters, used for amplitude correction of the pre-processed first vibration signal based on pre-stored amplitude gain adjustment parameters to obtain a second vibration signal, and for gradient noise elimination of the pre-processed initial speech signal based on the second vibration signal to obtain a target speech signal.

[0013] Optionally, in the above technical solution, the central control console includes: a central control console control module, including a first gain module, the first gain module being connected to a first signal processing module via an optical fiber link, used for gain control of the target voice signal; and a first voice output module, connected to the first gain module and the first voice playback module, used for sequentially performing digital-to-analog conversion, filtering, and amplification on the gain-controlled target voice signal to generate a target voice analog signal, and sending the target voice analog signal to the first voice playback module for playback.

[0014] Optionally, in the above technical solution, the system further includes a patient alarm module, the voice control device further includes a second signal processing module, and the central control module further includes a first selection module and a sound mixer connected to the first selection module; the patient alarm module is used to collect the patient's alarm actions; the second signal processing module is used to receive the alarm actions and convert the alarm actions into patient alarm trigger signals; the first selection module is connected to the second signal processing module via an optical fiber link and is used to select and control the patient alarm trigger signals; wherein, the first voice output module is connected to the sound mixer and is also used to sequentially perform digital-to-analog conversion, filtering, and amplification on the patient alarm trigger signals to generate alarm trigger analog signals, and to send the alarm trigger analog signals to the first voice playback module for playback, and the first gain module is connected to the first voice output module via the sound mixer.

[0015] Optionally, in the above technical solution, the central control unit also includes an alarm deactivation module connected to the first selection module. The alarm deactivation module is used to receive an alarm deactivation signal from the operator to deactivate the patient's alarm trigger signal, and the first selection module is used to deactivate the patient's alarm trigger signal according to the alarm deactivation signal.

[0016] Optionally, in the above technical solution, the central control unit further includes an audio signal input terminal for the operating computer, a third signal processing module, and a second gain module. The central control unit control module also includes a second selection module connected to the sound mixer. The third signal processing module, connected to the audio signal input terminal for the operating computer, is used to sequentially filter, amplify, and convert the computer audio signal to digital to generate a computer audio processing signal. The second gain module, connected to the third signal processing module, is used to control the gain of the computer audio processing signal. The second selection module, connected to the second gain module, is used to control whether the gain-controlled computer audio processing signal is input to the sound mixer. The first voice output module is also used to sequentially convert the computer audio processing signal to analog, filter, and amplify it to generate a first computer audio analog signal, and to send the first computer audio analog signal to the first voice playback module for playback.

[0017] Optionally, in the above technical solution, the system includes a second voice playback module, and the voice control device further includes a second voice output module; the second voice output module is connected to the second gain module via an optical fiber link, and is used to sequentially perform digital-to-analog conversion, filtering, and amplification on the computer audio processing signal to generate a second computer audio analog signal; the second voice playback module is connected to the second voice output module and is used to play the second computer audio analog signal.

[0018] In the above technical solution, optionally, the system includes an operator voice acquisition module, the central control console includes a fourth signal processing module, and the central control console control module includes a third gain module and a third selection module; the operator voice acquisition module is used to acquire operator voice signals; the fourth signal processing module is connected to the operator voice acquisition module and is used to sequentially filter, amplify, and perform analog-to-digital conversion on the operator voice signals to generate operator voice processing signals; the third gain module is connected to the fourth signal processing module and is used to perform gain control on the operator voice processing signals; the third selection module is connected to the second and third gain modules and is used to control whether the gain-controlled computer audio processing signals and / or operator voice processing signals are input to the second voice output module; the second voice output module is also used to sequentially perform digital-to-analog conversion, filtering, and amplification on the operator voice processing signals to generate operator voice analog signals; the second voice playback module is also used to play the operator voice analog signals.

[0019] In the above technical solution, optionally, the first, second and third selection modules are selected by a touch screen and screen control module or a mechanical switch; and / or, the first, second and third gain modules are gained by a touch screen and screen control module or a rotary encoder.

[0020] Optionally, in the above technical solution, the system further includes a device hub, and the central control module further includes an information packaging module and a gesture control parsing module. The central control module also includes a touch screen and a screen control module. The touch screen and screen control module are used to input control signals. The gesture control parsing module is connected to the touch screen and screen control module and is used to parse the control signals and generate first device control data. The information packaging module is connected to the gesture control parsing module and is used to package the first device control data. The device hub is connected to the information packaging module and related equipment of the magnetic resonance imaging system via an optical fiber link. It is used to receive the packaged first device control data and send the first device control data to the related equipment to control the operation of the related equipment; and to receive device status data from the related equipment and send the device status data to the information packaging module. The touch screen and screen control module is also used to receive device status data from the information packaging module and display the device status data.

[0021] Optionally, in the above technical solution, the central control console further includes a voice recognition processing module, and the central control console control module further includes a voice recognition parsing module and an information packaging module; the voice recognition processing module, connected to the operator voice acquisition module, is used to recognize the operator's voice signal; the voice recognition parsing module, connected to the voice recognition processing module, is used to parse the operator's voice signal and generate second equipment control data; the information packaging module, also connected to the voice recognition parsing module, is used to package the second equipment control data; the equipment hub is also used to receive the packaged second equipment control data and send the second equipment control data to relevant equipment to control the operation of the relevant equipment.

[0022] In the above technical solution, optionally, the central control console is located in the operating room, and the voice control equipment is located in the scanning room.

[0023] In this embodiment, pre-stored amplitude gain adjustment parameters and signal readout delay time are acquired. At the first moment during the magnetic resonance scanning process, a vibration sensor is used to acquire the first vibration signal of the gradient coil of the magnetic resonance imaging system. After the signal readout delay time, the patient's initial speech signal is acquired using the patient speech acquisition module. Furthermore, gradient noise in the patient's initial speech signal is eliminated to obtain the target speech signal after gradient noise removal, enabling real-time voice interaction between the patient and the operator during the magnetic resonance scanning process.

[0024] The embodiments of this application can reduce gradient noise generated during magnetic resonance scanning, reduce the impact on the patient's voice signal, and realize two-way voice communication between doctors and patients during magnetic resonance scanning.

[0025] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0026] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0027] Figure 1 A flowchart illustrating the speech signal acquisition method according to an embodiment of this application is shown;

[0028] Figure 2 A structural diagram of the control system of the magnetic resonance imaging system according to an embodiment of this application is shown;

[0029] Figure 3 A structural diagram of the central control console according to an embodiment of this application is shown;

[0030] Figure 4 A structural diagram of a voice control device according to an embodiment of this application is shown;

[0031] Figure 5 A structural diagram of a device hub according to an embodiment of this application is shown;

[0032] Figure 6 A flowchart illustrating the amplitude matching and delay calibration operation algorithm of an embodiment of this application is shown;

[0033] Figure 7 A structural diagram of a computer device according to an embodiment of this application is shown. Detailed Implementation

[0034] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0035] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0036] The following description, in conjunction with the accompanying drawings, details the speech signal acquisition method, speech control device, magnetic resonance imaging system control system, computer equipment, and readable storage medium provided in this application through specific embodiments and application scenarios.

[0037] This application provides a method for acquiring voice signals, applied to the control system of a magnetic resonance imaging system. For example... Figure 1 As shown, the method includes:

[0038] Step 101: Acquire the first vibration signal of the gradient coil of the magnetic resonance imaging system, and after a pre-stored signal reading delay time, acquire the patient's initial speech signal, and preprocess the first vibration signal and the initial speech signal.

[0039] Step 102: Based on the pre-stored amplitude gain adjustment parameters, perform amplitude correction on the pre-processed first vibration signal to obtain the second vibration signal;

[0040] Step 103: Based on the second vibration signal, gradient noise is eliminated from the preprocessed initial speech signal to obtain the target speech signal.

[0041] In this embodiment, pre-stored amplitude gain adjustment parameters and signal readout delay time are acquired. During the first moment of the magnetic resonance scanning process, a vibration sensor acquires the first vibration signal of the gradient coil of the magnetic resonance imaging system. After the signal readout delay time, the patient's initial speech signal is acquired using the patient speech acquisition module, enabling delay calibration of the initial speech signal. Further, the first vibration signal and the initial speech signal are pre-processed. The amplitude of the pre-processed first vibration signal is corrected according to the pre-stored amplitude gain adjustment parameters to obtain a second vibration signal. Based on the second vibration signal, gradient noise in the pre-processed initial speech signal is eliminated to obtain the target speech signal after gradient noise elimination, enabling real-time voice interaction between the patient and the operator during the magnetic resonance scanning process.

[0042] The embodiments of this application can reduce gradient noise generated during magnetic resonance scanning, reduce the impact on the patient's voice signal, and realize two-way voice communication between doctors and patients during magnetic resonance scanning.

[0043] In one embodiment of this application, the amplitude of a preprocessed first vibration signal is corrected based on a pre-stored amplitude gain adjustment parameter to obtain a second vibration signal, including: multiplying the preprocessed first vibration signal with the pre-stored amplitude gain adjustment parameter to obtain the second vibration signal; and performing gradient noise elimination on the preprocessed initial speech signal based on the second vibration signal to obtain a target speech signal, including: subtracting the preprocessed initial speech signal from the second vibration signal to obtain the target speech signal.

[0044] In this embodiment, the first vibration signal V1 is multiplied by the amplitude gain adjustment parameter ΔA to obtain the second vibration signal V2. The patient's initial speech signal SA, which is read after the signal reading delay time ΔT, is subtracted from the second vibration signal V2 to obtain the subtraction result S_denoise, that is, S_denoise = SA - V1 × ΔA. S_denoise is the patient's target speech signal after removing gradient noise.

[0045] By using the above methods, gradient noise generated by the magnetic resonance imaging system during the scanning process can be eliminated, enabling real-time two-way voice communication between the patient and the operator during the magnetic resonance imaging system scan.

[0046] In one embodiment of this application, the method for obtaining signal readout delay time and amplitude gain adjustment parameters includes: when debugging or calibrating the magnetic resonance imaging system, acquiring a first audio noise from the patient's voice acquisition module and a third vibration signal acquired by the vibration sensor; acquiring amplitude gain adjustment parameters and signal readout delay time based on the first audio noise and the third vibration signal; wherein the amplitude gain adjustment parameter is the ratio of the maximum amplitude of the preprocessed first audio noise to the maximum amplitude of the preprocessed third vibration signal; and the signal readout delay time is the difference between the occurrence time of the maximum amplitude of the preprocessed first audio noise and the occurrence time of the maximum amplitude of the preprocessed third vibration signal.

[0047] Specifically, the system reads a first audio noise and a third vibration signal, determines the maximum amplitude of the first audio noise and the time when the maximum amplitude of the first audio noise occurs, and determines the maximum amplitude of the third vibration signal and the time when the maximum amplitude of the third vibration signal occurs; calculates the ratio of the maximum amplitude of the first audio noise to the maximum amplitude of the third vibration signal, and calculates the target time interval between the time when the maximum amplitude of the first audio noise occurs and the time when the maximum amplitude of the third vibration signal occurs; reads a fourth vibration signal, calculates the product of the fourth vibration signal and the ratio to obtain a fifth vibration signal, and reads the second audio noise after the target time interval; calculates the correlation coefficient between the fifth vibration signal and the second audio noise, and if the correlation coefficient is greater than or equal to the correlation coefficient threshold, stores the ratio as an amplitude gain adjustment parameter, and stores the target time interval as a signal reading delay time.

[0048] In this embodiment, once the magnetic resonance imaging system is installed and the mechanical assembly relationship is fixed, the frequency characteristics of the mechanical vibration are determined. Therefore, during the system calibration phase, the scanning system calibration phase, or the system debugging phase, the patient voice acquisition module collects the audio signal generated during the magnetic resonance scanning process in the scanning room, and the vibration sensor collects the vibration signal generated during the magnetic resonance scanning process in the scanning room. Then, amplitude matching and delay calibration operations are performed on the audio signal and the vibration signal to obtain the amplitude gain adjustment parameter ΔA of the vibration signal and the signal delay reading time ΔT of the audio signal. The amplitude gain adjustment parameter ΔA of the vibration signal and the signal delay reading time ΔT of the audio signal are then stored.

[0049] Specifically, during the system calibration phase, or the scanning system calibration phase, or the system debugging phase, the first audio noise N1 and the third vibration signal V3 are read, and the maximum amplitude NA_max of the first audio noise and the occurrence time NT_max of the maximum amplitude NA_max of the first audio noise are determined, as are the maximum amplitude VA_max of the third vibration signal and the occurrence time VT_max of the maximum amplitude VA_max of the third vibration signal; the ratio of the maximum amplitude NA_max of the first audio noise to the maximum amplitude VA_max of the third vibration signal is calculated, and the occurrence time of the maximum amplitude NA_max of the first audio noise is calculated. The target time interval between NT_max and the occurrence time of the maximum amplitude VA_max of the third vibration signal VT_max; read the fourth vibration signal V4 and calculate the product of the fourth vibration signal V4 and the ratio to obtain the fifth vibration signal V5, and read the second audio noise N2 after the target time interval; calculate the correlation coefficient C between the fifth vibration signal V5 and the second audio noise N2, specifically based on the covariance Cov(V5,N2) of the fifth vibration signal V5 and the second audio noise N2, the variance Var[V5] of the fifth vibration signal V5, and the variance Var[N2] of the second audio noise N2. The calculation formula is as follows: If the correlation coefficient C is greater than or equal to the correlation coefficient threshold CT, the ratio is stored as the amplitude gain adjustment parameter ΔA, and the target time interval is stored as the signal readout delay time ΔT.

[0050] Then, during the subsequent formal clinical scanning process, the amplitude gain adjustment parameter ΔA and the signal readout delay time ΔT are used to eliminate the gradient noise generated during the scanning process.

[0051] This application provides a fully digital integrated multimedia control system for a magnetic resonance imaging system. For example... Figure 2As shown, the system includes: a central control console, a voice control device, a vibration sensor, a patient voice acquisition module (e.g., a patient microphone), a patient alarm module (e.g., a patient pneumatic alarm ball), a first voice playback module (e.g., an external microphone), a patient monitoring camera, an operator voice acquisition module (e.g., an operator microphone), an operating computer audio signal input terminal, a second voice playback module (e.g., an external microphone), and a device hub. The central control unit is interconnected with the patient monitoring camera via a patient monitoring data communication fiber optic link, with the equipment hub via a device control and status data communication fiber optic link, and with the voice control device via operator voice and computer audio signal fiber optic links, patient voice signal fiber optic links, and patient alarm trigger signal links. It also receives input from the operator voice acquisition module and the computer audio signal input terminal, and controls the output of the first voice playback module. The voice control device is interconnected with the central control unit control module via operator voice and computer audio signal fiber optic links, patient voice signal fiber optic links, and patient alarm trigger signal links. It also receives input from the patient voice acquisition module, vibration sensor, and patient alarm module, and controls the output of the second voice playback module. The equipment hub is interconnected with the air conditioning unit, patient ventilation system, patient scanning bed, magnet management unit, water-cooled unit, gradient amplifier, spectrometer, RF amplifier, and power distribution unit via fiber optic links and cables. It is also interconnected with the central control unit via a device control and status data communication fiber optic link.

[0052] Center console, such as Figure 3 As shown, it includes a third signal processing module, a fourth signal processing module, a first voice output module, a central control module, a touch screen and screen control module, a voice recognition and processing module, as well as a scanning room voice selection switch (i.e., a mechanical switch), a scanning room volume adjustment rotary encoder, an operating room audio switch (i.e., a mechanical switch), a patient volume adjustment rotary encoder, an emergency quench button, a system power on / off button, a scanning bed removal button, an emergency bed stop button, an alarm deactivation module, fiber optic connector 1, fiber optic connector 2, fiber optic connector 3, and fiber optic connector 7.

[0053] The third signal processing module includes a signal conditioning submodule 6 and an analog-to-digital converter (A / D-4); the fourth signal processing module includes a signal conditioning submodule 5 and an analog-to-digital converter (A / D-3); the first voice output module includes a digital-to-analog converter (D / A-2), a signal conditioning submodule 3, and an audio driver 1; the central control module consists of a gain control submodule 1 (i.e., the first gain module), a gain control submodule 2 (i.e., the second gain module), a gain control submodule 3 (i.e., the third gain module), selector 1 (i.e., the first selection module), selector 2 (i.e., the second selection module), selector 3 (i.e., the third selection module), a sound mixer, an alarm tone generator, a gesture control parsing module, a voice recognition parsing module, an information packaging module, and communication interfaces 1, 2, 3, 7, and 8.

[0054] Voice control devices, such as Figure 4 As shown, it includes a second voice output module, a first signal processing module, a second signal processing module (i.e., a pneumatic-to-electrical conversion module), an optical fiber connector 4, and an optical fiber connector 5. The second voice output module includes a communication interface 4, a digital-to-analog converter (D / A-1), a signal conditioning submodule 4, and an audio driver 2. The first signal processing module includes a signal conditioning submodule 1 (i.e., the first signal conditioning module), a signal conditioning submodule 2 (i.e., the second signal conditioning module), an analog-to-digital converter (A / D-1) (i.e., the first analog-to-digital converter), an analog-to-digital converter (A / D-2) (i.e., the second analog-to-digital converter), a noise reduction module, a memory, and the communication interface 5.

[0055] Equipment hubs, such as Figure 5 As shown, it includes a device control data parsing submodule, a device status information packaging submodule, a device control and communication interface submodule, a fiber optic connector 6, and a communication interface 6.

[0056] The fourth signal processing module of the central control unit receives the operator's voice signal from the operator's voice acquisition module, while the third signal processing module receives the computer audio signal input from the computer's audio signal input terminal. The operator's voice signal, after being low-pass filtered and amplitude adjusted by the signal conditioning submodule 5, is sent to the analog-to-digital converter A / D-3 to convert the analog operator's voice signal into a digitized operator processing signal. Finally, the digitized operator processing signal is output to the gain control submodule 3 in the central control unit's control module for gain control. Similarly, the computer audio signal, after being low-pass filtered and amplitude adjusted by the signal conditioning submodule 6, is sent to the analog-to-digital converter A / D-4 to convert the analog computer audio signal into a digitized computer audio processing signal. Finally, the digitized computer audio processing signal is output to the gain control submodule 2 in the central control unit's control module for gain control.

[0057] Gain control submodule 3 can receive gain control commands from the operator's voice signals from the scanning room volume adjustment rotary encoder, touch screen and screen control module, and voice recognition and processing module, realizing multimedia control of the gain of the operator's voice processing signal. The output of gain control submodule 3 serves as one of the inputs of selector submodule 3. Gain control submodule 2 can receive gain control commands from the computer audio signals from the scanning room volume adjustment rotary encoder, touch screen and screen control module, and voice recognition and processing module, realizing multimedia control of the gain of the computer audio processing signal. The output of gain control submodule 2 serves as one of the inputs of selector submodule 3.

[0058] Selector 3 submodule receives selection commands from the scanning room voice selection switch, touch screen and screen control module, and voice recognition and processing module, enabling multimedia to select and control the operator's voice processing signal and the computer's audio processing signal. The selected operator's voice processing signal or computer's audio processing signal from selector 3 submodule enters communication interface 1 submodule. Communication protocol packaging is completed in communication interface 1 submodule, and the signal is output to the voice control device's fiber optic connector 4 via fiber optic connector 1 and the fiber optic link between the operator's voice and the computer's audio signal.

[0059] The operator's voice processing signal and the computer's audio processing signal, input from the fiber optic connector 4 of the voice control device, enter the second voice output module, such as... Figure 4 As shown, data is unpacked in communication interface 4, converted into an analog signal by digital-to-analog converter D / A-1, and input to signal conditioning submodule 4 for low-pass filtering and signal pre-amplification. Then, audio driver 2 drives the second voice playback module to emit the operator's voice, as well as the computer audio music or scanning automatic broadcast voice of the operating computer.

[0060] The second signal processing module in the voice control device converts the pressing alarm action of the patient alarm module into a patient alarm trigger signal, and outputs it to the central control module of the central control console via the patient alarm trigger signal link.

[0061] The magnetic resonance imaging (MRI) system includes a magnet housing and a patient scanning bed. Gradient coils are housed within the magnet housing. The patient scanning bed includes a bed frame and a bed plate. The bed frame is fixed relative to the magnet housing, while the bed plate can enter and exit the magnet housing through its port. The audio noise generated during scanning in the MRI system's scanning chamber originates from the Lorentz force vibration generated by the pulsed gradient field. Since both the magnet and the gradient coils are rigid objects, theoretically, the patient voice acquisition module can be mounted anywhere within the scanning chamber, and the vibration sensor can be mounted anywhere on the gradient coil. However, considering the need to ensure the intensity of the acquired audio sound and the operational reliability of the vibration sensor, this embodiment places the patient voice acquisition module on the magnet housing at the port of the scanning cavity enclosed by the magnet housing, and the vibration sensor is mounted on the gradient coil within the magnet housing. For example, the patient voice acquisition module can be mounted on the top of the port of the magnet housing, and the vibration sensor can be mounted in the central region of the gradient coil within the magnet housing.

[0062] During the system calibration phase after installation, or the scanning system calibration phase, or the system debugging phase, the patient voice acquisition module collects the audio noise generated during the MRI scan in the scanning room. Simultaneously, a vibration sensor collects the vibration signals generated during the MRI scan in the scanning room. The first signal processing module in the voice control device simultaneously receives the audio noise from the patient voice acquisition module and the vibration signal from the vibration sensor. The audio noise is low-pass filtered and its amplitude adjusted by the signal conditioning submodule 1, and then sent to the analog-to-digital converter A / D-1 to convert the analog audio noise into digital audio noise. Finally, the digitized audio noise is output to the denoising module. Similarly, the vibration signal is low-pass filtered and its amplitude adjusted by the signal conditioning submodule 2, and then sent to the analog-to-digital converter A / D-2 to convert the analog vibration signal into a digital vibration signal. Finally, the digitized vibration signal is output to the denoising module. The noise reduction module simultaneously receives audio noise and vibration signals. It performs signal amplitude matching and delay calibration on the audio noise and vibration signals to obtain the amplitude gain adjustment parameter ΔA of the vibration signal and the signal delay reading time ΔT of the audio noise. It then stores the amplitude gain adjustment parameter ΔA and the signal delay reading time ΔT. The algorithm flow for this amplitude matching and delay calibration operation is as follows: Figure 6As shown, the correlation coefficient threshold CT between the vibration signal and audio noise is set, the scan is started, and analog-to-digital converters A / D-1 and A / D-2 are reset simultaneously. One frame of audio noise and one frame of vibration signal are read. The maximum amplitude NA_max of the audio noise and its occurrence time NT_max, and the maximum amplitude VA_max of the vibration signal and its occurrence time VT_max are recorded. The ratio ΔA of NA_max to VA_max is calculated, and the target time interval ΔT between NT_max and VT_max is calculated. A new frame of vibration signal is read, and the amplitude of the new frame of vibration signal is modified using the ratio. A new frame of audio noise is read after a delay of the target time interval. The correlation coefficient C between the new frame of vibration signal and the new frame of audio noise is calculated. It is determined whether the correlation coefficient C is greater than or equal to the correlation coefficient threshold CT. If it is greater than or equal to CT, the ratio ΔA and the target time interval ΔT are recorded and stored. If it is less than CT, the process returns, and analog-to-digital converters A / D-1 and A / D-2 are reset simultaneously. Here, the ratio is the amplitude gain adjustment parameter, and the target time interval is the signal reading delay time.

[0063] During the routine clinical scanning phase or the scanning process after sequence calibration, the first signal processing module in the voice control device simultaneously receives the patient's initial speech signal from the patient's speech acquisition module and the first vibration signal from the vibration sensor. The initial speech signal, after low-pass filtering and amplitude adjustment by the signal conditioning submodule 1, is sent to the analog-to-digital converter A / D-1 to convert the analog initial speech signal into a digital initial speech signal. Finally, the digitized initial speech signal is output to the denoising module. Similarly, the first vibration signal, after low-pass filtering and amplitude adjustment by the signal conditioning submodule 2, is sent to the analog-to-digital converter A / D-2 to convert the analog first vibration signal into a digital first vibration signal. Finally, the digitized first vibration signal is output to the denoising module. Specifically, the denoising module reads the amplitude gain adjustment parameter ΔA and the signal delay readout time ΔT from the memory, reads the first vibration signal V1, and reads the initial speech signal SA during the delay readout time ΔT. It multiplies the first vibration signal V1 with the amplitude gain adjustment parameter ΔA to obtain the second vibration signal V2. It then subtracts the initial speech signal SA from the second vibration signal V2 to obtain the subtraction result S_denoise, i.e., S_denoise = SA - V1 × ΔA. S_denoise is the patient's target speech signal after removing gradient noise, thereby eliminating the gradient noise generated by the magnetic resonance imaging system during scanning and enabling real-time two-way voice communication between the patient and the operator during the magnetic resonance imaging system scan. The communication interface 5 packages the target speech signal after removing gradient noise using a communication protocol and outputs it to the fiber optic connector 2 of the central control unit via the fiber optic connector 5 and the patient's speech signal fiber optic link.

[0064] The patient's target voice signal, input from fiber optic connector 2 on the central control panel, enters the central control panel control module, such as... Figure 3 As shown, the target speech signal undergoes communication data unpacking in communication interface 2, and the unpacked target speech signal is input to the gain control 1 submodule. The gain control 1 submodule receives gain control commands from the target speech signal from the scanning room volume adjustment rotary encoder, touch screen and screen control module, and speech recognition and processing module, controls the volume of the patient's speech, and finally inputs the gain-adjusted target speech signal to the sound mixer submodule.

[0065] In addition to receiving the target voice signal, the sound mixer submodule of the central control module also receives the computer audio signal selected by selector 2 and the patient alarm trigger signal (i.e., the alarm signal) selected by selector 1. Selector 2 controls whether the computer audio processing signal output by submodule 2 is fed into the sound mixer through the switching of the operating room audio switch, the operating room audio switch output by the touch screen and screen control module, and the operating room audio switch output by the voice recognition and processing module. Selector 1 enables the alarm signal output of the alarm tone generator through the patient alarm trigger signal from the voice control device, and disables the alarm signal output of the alarm tone generator through the alarm cancellation module, the alarm cancellation signal output by the touch screen and screen control module, and the alarm cancellation signal output by the voice recognition and processing module.

[0066] The patient's target speech signal, computer audio processing signal, and alarm signal are mixed by a sound mixer to form a sound signal, which is then output to the first voice output module of the central control panel. In the first voice output module, the sound signal is converted into an analog signal by a digital-to-analog converter (D / A-2), and then input to the signal conditioning submodule 3 for low-pass filtering and signal pre-amplification. The signal-conditioned sound signal, together with the automatically broadcast speech from the speech recognition and processing module, is input to the audio driver 1, which drives the first voice broadcast module to emit sound.

[0067] The central control unit's touchscreen and screen control module features communication interfaces such as high-definition multimedia interface (HDMI), general purpose I / O port (GPIO), and serial peripheral interface or asynchronous communication port (UART / SPI). The touchscreen can integrate virtualized sliders for scanning room volume control, patient volume control, scanning room voice selection switch, operator room audio switch, alarm deactivation module, emergency bed stop button, scanning bed removal button, system switch button, emergency queuing button, air conditioning temperature control slider and operating mode selection button, patient ventilation airflow selection button, or other types of virtual touch switches and virtual touch buttons. The physical scanning room voice selection switch and scanning room volume control rotary encoder, integrated into the central control unit, can be used as virtual switches, sliders, buttons, or menu selection and confirmation on the touchscreen, enabling control of the relevant equipment status of the MRI system. The touchscreen can display equipment status and operation prompts in graphic and textual format, facilitating human-computer interaction and doctor-patient interaction. The touchscreen can also display images captured by the scanning room monitoring camera in real time, enabling monitoring of the scanning status.

[0068] Through the GPIO interfaces of the touchscreen and screen control module, the virtual scanning room volume adjustment slider built into the touchscreen can control the gain control submodules 2 and 3 in the central control module, realizing gain control of the operator's voice processing signal and the computer audio processing signal; through the GPIO interfaces of the touchscreen and screen control module, the virtual patient volume adjustment slider built into the touchscreen can control the gain control submodule 1 in the central control module, realizing gain control of the patient's target voice signal; through the GPIO interfaces of the touchscreen and screen control module, the virtual scanning room voice selection switch built into the touchscreen can control the output selection of selector 3 in the central control module, realizing the switching between operator's voice processing signal and computer audio processing signal; through the GPIO interfaces of the touchscreen and screen control module, the virtual operating room audio switch built into the touchscreen can control the output of selector 2 in the central control module, realizing the playback on / off control of computer audio music or automatic scanning announcement voice in the operating room; through the GPIO interfaces of the touchscreen and screen control module, the virtual alarm deactivation module built into the touchscreen can control the output of selector 1 in the central control module, realizing the deactivation control of alarm sounds.

[0069] Through the GPIO interface of the speech recognition and processing module, the command codes generated from the recognition results of the operator's voice commands for adjusting the scanning room volume can control the gain control submodules 2 and 3 in the central control module, thereby achieving gain control of the operator's voice processing signal and the computer's audio processing signal. Similarly, through the GPIO interface of the speech recognition and processing module, the command codes generated from the recognition results of the operator's voice commands for adjusting the patient's volume can control the gain control submodule 1 in the central control module, thereby achieving gain control of the patient's target voice signal. Finally, through the GPIO interface of the speech recognition and processing module, the command codes generated from the recognition results of the operator's voice commands for selecting the scanning room volume can control the gain control submodule 1 in the central control module, thereby achieving gain control of the patient's target voice signal. The generated instruction codes can control the output selection of selector 3 in the central control module, enabling the switching between operator voice processing signals and computer audio processing signals; through the GPIO interface of the voice recognition and processing module, the instruction codes generated based on the voice recognition results of the operator's voice prompts for the control room audio switch can control the output of selector 2 in the central control module, enabling the playback switch control of computer audio music or automatic scanning announcements in the control room; through the GPIO interface of the voice recognition and processing module, the instruction codes generated based on the recognition results of the operator's alarm cancellation voice prompts can control the output of selector 1 in the central control module, enabling the cancellation control of alarm sounds.

[0070] The button operation information of the virtual emergency bed stop button, virtual scanning bed removal button, virtual system power on / off button, and virtual emergency queuing button built into the touch screen and screen control module, the operation information of the virtual temperature adjustment slider and working mode selection button of the air conditioning unit, and the operation information of the virtual air volume selection button of the patient ventilation system are uniformly encoded and packaged in the touch screen and screen control module to form a touch screen data packet. The touch screen data packet enters the communication interface 7 of the central control module through the serial peripheral interface or asynchronous communication port (UART / SPI) of the touch screen and screen control module via the touch screen data channel. After the touch screen data is unpacked at the communication interface 7, it enters the gesture control parsing module for data parsing to form the first category of equipment control data. The parsed and categorized first equipment control data enters the information packaging module through the equipment control and status data 1 channel.

[0071] The command codes generated from the voice recognition results of emergency bed stop, scanning bed removal, system power on / off, and emergency quenching failure, the command codes generated from the voice recognition results of air conditioning temperature adjustment and operating mode, and the command codes generated from the voice recognition results of patient ventilation airflow selection are uniformly encoded and packaged in the voice recognition and processing module to form a voice recognition data packet. The voice recognition data packet enters the communication interface 8 of the central control module via the voice recognition data channel through the serial peripheral interface or asynchronous communication port (UART / SPI) of the voice recognition and processing module. After unpacking the voice recognition data at communication interface 8, it enters the voice recognition parsing module for data parsing, forming classified second-level equipment control data. The parsed and classified second-level equipment control data enters the information packaging module via the equipment control and status data 2 channel.

[0072] The action status data of physical buttons such as the emergency stop button, the scanning bed removal button, the system switch button, and the emergency queuing button on the central control console are directly input into the information packaging module of the central control console control module.

[0073] The information packaging module of the central control unit receives first equipment control data from the touch screen and screen control module, second equipment control data from the voice recognition and processing module, and action status data from physical buttons such as the emergency stop button, the scanning bed removal button, the system switch button, and the emergency queuing button. It then performs unified information packaging processing on the data to form unified equipment control data, which is input to the communication module 3 through the equipment control and status data channel. The fiber optic communication protocol is converted at the communication interface 3, and the data is output to the equipment hub through the fiber optic connector 3 of the central control unit and the equipment control and status data communication fiber optic link.

[0074] Device control data entering the device hub is unpacked via fiber optic connector 6 into the communication interface and then input to the device control data parsing module for classification. The classified device control data is then sent to the corresponding device connector of the device control and communication interface module to communicate with the corresponding controlled device, controlling the working status and mode of devices such as air conditioning units, patient ventilation systems, patient scanning beds, magnet management units, water-cooled units, gradient amplifiers, spectrometers, radio frequency amplifiers, and power distribution units.

[0075] Status data from devices such as air conditioning units, patient ventilation systems, patient scanning beds, magnet management units, water-cooled units, gradient amplifiers, spectrometers, radio frequency amplifiers, and power distribution units are transmitted through their respective device connectors to the device control and communication interface module of the device hub for communication protocol conversion to obtain unified device status data. The obtained device status data is then input to the device status information packaging module for data packaging, undergoes fiber optic protocol conversion at communication interface 6, and enters the central control console via fiber optic connector 6 and the device control and status data communication fiber optic link.

[0076] Device status data entering the central control console via fiber optic connector 3 first undergoes communication protocol conversion at communication interface 3 of the central control module. Then, it is input to the information packaging module via the device control and status data channel. In the information packaging module, the device status data is routed to the device control and status data channel 1 and output to communication interface 7 via the gesture control parsing module. Communication interface 7 performs communication protocol conversion on the device status data, which then enters the touchscreen and screen control module via UART or SPI port. The central control console touchscreen displays the status of devices such as air conditioning units, patient ventilation systems, patient scanning beds, magnet management units, water-cooled units, gradient amplifiers, spectrometers, RF amplifiers, and power distribution units. Based on the displayed device status, the touchscreen can provide alarm prompts in both graphic and textual formats.

[0077] When the central control console's touchscreen and control module have several virtual function buttons, switches, sliders, and menus that need to be selected or operated, the scanning room voice selection switch and the scanning room volume adjustment rotary encoder can be used as a second operation method. That is, the knob of the scanning room volume adjustment rotary encoder can move the cursor on the touchscreen to select the corresponding virtual function button, switch, slider, and menu. After selecting the corresponding virtual function button, switch, slider, and menu, pressing the scanning room voice selection switch confirms the selected virtual function button, switch, slider, and menu, thus completing the control of the MRI equipment.

[0078] This application also provides a computer device, such as... Figure 7 As shown, the computer device 700 includes a processor 701 and a memory 702. The memory 702 stores a program or instruction that can run on the processor 701. When the program or instruction is executed by the processor 701, it implements the various steps of the above-described speech signal acquisition method embodiment and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0079] It should be noted that the computer devices in the embodiments of this application include the mobile computer devices and non-mobile computer devices described above.

[0080] The memory 702 can be used to store software programs and various data. The memory 702 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory 702 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 702 in this embodiment includes, but is not limited to, these and any other suitable types of memory.

[0081] Processor 701 may include one or more processing units; optionally, processor 701 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into processor 701.

[0082] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described speech signal acquisition method embodiments and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0083] This application also provides a chip, which includes a processor and a communication interface. The communication interface and the processor are coupled. The processor is used to run programs or instructions to implement the various processes of the above-described voice signal acquisition method embodiments and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0084] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0085] This application also provides a computer program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the above-described speech signal acquisition method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0086] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0087] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A control system of a magnetic resonance imaging system, characterized in that, include: Vibration sensor, used to acquire the first vibration signal of the gradient coil of the magnetic resonance imaging system; The patient voice acquisition module is used to acquire the patient's initial voice signal after a pre-stored signal reading delay time. A voice control device includes a first signal processing module, which is connected to the vibration sensor and the patient voice acquisition module respectively. The first signal processing module is used to receive and preprocess the first vibration signal and the initial voice signal, and to perform amplitude correction on the preprocessed first vibration signal based on a pre-stored amplitude gain adjustment parameter to obtain a second vibration signal. Based on the second vibration signal, gradient noise is eliminated on the preprocessed initial voice signal to obtain a target voice signal. The central control unit is connected to the first signal processing module and is used to acquire the target voice signal and send the target voice signal to the first voice playback module. The first voice playback module is connected to the central control unit and is used to play the target voice signal.

2. The system of claim 1, wherein, The first signal processing mold body is used to: multiply the preprocessed first vibration signal with the amplitude gain adjustment parameter to obtain the second vibration signal; and subtract the preprocessed initial speech signal from the second vibration signal to obtain the target speech signal.

3. The system of claim 1, wherein, The first signal processing module is also used for: When debugging or calibrating the magnetic resonance imaging system, the first audio noise from the patient's voice acquisition module and the third vibration signal from the vibration sensor are acquired. Based on the first audio noise and the third vibration signal, the amplitude gain adjustment parameter and the signal reading delay time are obtained. The amplitude gain adjustment parameter is the ratio of the maximum amplitude of the preprocessed first audio noise to the maximum amplitude of the preprocessed third vibration signal. The signal reading delay time is the difference between the occurrence time of the maximum amplitude of the preprocessed first audio noise and the occurrence time of the maximum amplitude of the preprocessed third vibration signal.

4. The system according to claim 1, characterized in that, The patient voice acquisition module is mounted on the magnet housing and located at the port of the scanning cavity enclosed by the magnet housing; The vibration sensor is mounted on a gradient coil inside the magnet housing.

5. The system of claim 1, wherein, The first signal processing module includes: The first signal conditioning module is connected to the patient voice acquisition module and is used to perform low-pass filtering and amplification processing on the initial audio signal; A first analog-to-digital converter, connected to the first signal conditioning module, is used to perform analog-to-digital conversion on the amplified initial speech signal to generate a pre-processed initial speech signal. The second signal conditioning module is connected to the vibration sensor and is used to perform low-pass filtering and amplification processing on the first vibration signal; The second analog-to-digital converter is connected to the second signal conditioning module and is used to perform analog-to-digital conversion on the amplified first vibration signal to generate a pre-processed first vibration signal. The noise reduction module, connected to the first analog-to-digital converter and the second analog-to-digital converter, is used to perform amplitude correction on the preprocessed first vibration signal based on the pre-stored amplitude gain adjustment parameters, obtain the second vibration signal, and perform gradient noise elimination on the preprocessed initial speech signal based on the second vibration signal to obtain the target speech signal.

6. The system of claim 5, wherein, The central control panel includes: The central control module includes a first gain module, which is connected to the first signal processing module via an optical fiber link, and is used to control the gain of the target voice signal. The first voice output module, connected to the first gain module and the first voice playback module, is used to sequentially perform digital-to-analog conversion, filtering, and amplification on the target voice signal after gain control to generate a target voice analog signal, and to send the target voice analog signal to the first voice playback module for playback.

7. The system of claim 6, wherein, The system also includes a patient alarm module, the voice control device also includes a second signal processing module, and the central control module also includes a first selection module and a sound mixer connected to the first selection module. The patient alarm module is used to collect patients' alarm actions; The second signal processing module is used to receive the alarm action and convert the alarm action into a patient alarm trigger signal; The first selection module is connected to the second signal processing module via an optical fiber link, and is used to select and control the patient alarm trigger signal; The first voice output module, connected to the sound mixer, is also used to sequentially perform digital-to-analog conversion, filtering, and amplification on the patient alarm trigger signal to generate an alarm trigger analog signal, and to send the alarm trigger analog signal to the first voice playback module for playback. The first gain module is connected to the first voice output module through the sound mixer.

8. The system of claim 7, wherein, The central control unit also includes an alarm deactivation module connected to the first selection module. The alarm deactivation module is used to receive an alarm deactivation signal from the operator to deactivate the patient's alarm trigger signal. The first selection module is used to deactivate the patient's alarm trigger signal according to the alarm deactivation signal.

9. The system of claim 7, wherein, The central control unit also includes an audio signal input terminal for an operating computer, a third signal processing module, and a second gain module. The central control unit control module also includes a second selection module connected to the sound mixer. The third signal processing module is connected to the audio signal input terminal of the operating computer and is used to sequentially filter, amplify and convert the computer audio signal to digital to generate a computer audio processing signal. The second gain module is connected to the third signal processing module and is used to perform gain control on the computer audio processing signal; The second selection module, connected to the second gain module, is used to control whether the gain-controlled computer audio processing signal is input into the sound mixer; The first voice output module is further configured to sequentially perform digital-to-analog conversion, filtering, and amplification on the computer audio processing signal to generate a first computer audio analog signal, and to send the first computer audio analog signal to the first voice playback module for playback.

10. The system of claim 9, wherein, The system includes a second voice playback module, and the voice control device further includes a second voice output module; The second voice output module is connected to the second gain module via an optical fiber link, and is used to sequentially perform digital-to-analog conversion, filtering, and amplification on the computer audio processing signal to generate a second computer audio analog signal; The second voice playback module is connected to the second voice output module and is used to play the second computer audio analog signal.

11. The system of claim 10, wherein, The system includes an operator voice acquisition module, and the central control unit also includes a fourth signal processing module. The central control unit control module also includes a third gain module and a third selection module. The operator voice acquisition module is used to acquire the operator's voice signal; The fourth signal processing module is connected to the operator voice acquisition module and is used to sequentially filter, amplify and convert the operator voice signal to analog-to-digital conversion to generate the operator voice processing signal. The third gain module is connected to the fourth signal processing module and is used to perform gain control on the operator's voice processing signal. The third selection module, connected to the second and third gain modules, is used to control whether the computer audio processing signal and / or the operator voice processing signal, which are subject to gain control, are input into the second voice output module. The second voice output module is also used to sequentially perform digital-to-analog conversion, filtering, and amplification on the operator's voice processing signal to generate an analog voice signal of the operator; The second voice playback module is also used to play the operator's simulated voice signal.

12. The system according to claim 11, characterized in that, The first, second, and third selection modules are selected by a touch screen and screen control module or a mechanical switch; and / or, the first, second, and third gain modules are selected by a touch screen and screen control module or a rotary encoder.

13. The system according to claim 11, characterized in that, The system also includes a device hub, and the central control module further includes an information packaging module and a gesture control parsing module. The central control unit also includes a touch screen and a screen control module. The touchscreen and screen control module are used to input control signals; The gesture control parsing module is connected to the touch screen and screen control module, and is used to parse the control signal and generate the first device control data; The information packaging module is connected to the gesture control parsing module and is used to package the control data of the first device. The device hub is connected to the information packaging module and related devices of the magnetic resonance imaging system via an optical fiber link. It is used to receive the packaged first device control data and send the first device control data to the related devices to control the operation of the related devices; and to receive device status data from the related devices and send the device status data to the information packaging module. The touch screen and screen control module are also used to receive the device status data from the information packaging module and display the device status data.

14. The system according to claim 13, characterized in that, The central control unit also includes a voice recognition processing module, and the central control unit control module also includes a voice recognition parsing module and an information packaging module; The speech recognition processing module and the operator speech acquisition module are used to recognize the operator's speech signal; The speech recognition parsing module is connected to the speech recognition processing module and is used to parse the operator's speech signal and generate second device control data. The information packaging module is also connected to the voice recognition and parsing module, and is used to package the control data of the second device. The device hub is also configured to receive the packaged second device control data and send the second device control data to the relevant device to control the operation of the relevant device.

15. The system according to any one of claims 1 to 14, characterized in that, The central control console is located in the operating room, and the voice control device is located in the scanning room.

Images