Image generating apparatus, magnetic resonance imaging system, and image generating method

Abstract

To improve an imaging environment related to magnetic resonance imaging.SOLUTION: A video generation device includes an acquisition unit and a generation unit. The processing circuitry acquires patient information on a patient who undergoes imaging by a magnetic resonance imaging apparatus and examination information on imaging conditions. The generation unit generates video information by inputting patient information and examination information to a learned model trained to output a video based on the patient information and the examination information.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The embodiments disclosed in this specification and the drawings relate to an image generating device, a magnetic resonance imaging system, and an image generating method. [Background technology]

[0002] Magnetic resonance imaging (MRI) examinations can cause patients to feel anxious or confined due to the loud noises generated during the examination and the narrow, dark space inside the bore. To alleviate this anxiety and sense of claustrophobia, there is a technology that uses a projector and a reflector to project video images onto the inside of the MRI gantry.

[0003] The above technology projects an image suitable for the patient and the environment from pre-prepared images (preset images). In other words, the above technology has a limited number of image types, and the projected image may not necessarily be suitable for the patient. In this case, it may not be possible to reduce the anxiety or sense of claustrophobia felt by the patient inside the bore. Therefore, there is a need to improve the imaging environment for imaging using a magnetic resonance imaging apparatus. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2017-213039 Summary of the Invention [Problem to be solved by the invention]

[0005] One of the problems to be solved by the embodiments disclosed in this specification and the drawings is to improve the imaging environment for imaging using a magnetic resonance imaging apparatus. However, the problems to be solved by the embodiments disclosed in this specification and the drawings are not limited to the above problem. Problems corresponding to the effects of each configuration shown in the embodiments described below can also be positioned as other problems. [Means for solving the problem]

[0006] An image generating device according to an embodiment includes an acquisition unit and a generation unit. The acquisition unit acquires patient information about a patient undergoing imaging using a magnetic resonance imaging apparatus and examination information about imaging conditions. The generation unit generates image information by inputting the patient information and the examination information into a trained model that is trained to output an image based on the patient information and the examination information. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 1 is a block diagram illustrating the configuration of a magnetic resonance imaging system including a magnetic resonance imaging apparatus according to the first embodiment. [Figure 2] FIG. 2 is a diagram showing a specific example of the video generation process in the first embodiment. [Figure 3] FIG. 3 is a flowchart illustrating the operation of the processing circuit related to the video generation processing in the first embodiment. [Figure 4] FIG. 4 is a diagram showing a specific example of the video generation process in the second embodiment. [Figure 5] FIG. 5 is a flowchart illustrating the operation of the processing circuit related to the video generation processing in the second embodiment. [Figure 6] FIG. 6 is a block diagram illustrating the configuration of a processing circuit of a magnetic resonance imaging apparatus according to the third embodiment. [Figure 7] FIG. 7 is a diagram showing a specific example of the conversion process and the video generation process in the third embodiment. [Figure 8]FIG. 8 is a flowchart illustrating the operation of the processing circuit related to the conversion process and the video generation process in the third embodiment. [Figure 9] FIG. 9 is a diagram showing a specific example of the conversion process and the video generation process in the fourth embodiment. [Figure 10] FIG. 10 is a flowchart illustrating the operation of the processing circuit related to the conversion process and the video generation process in the fourth embodiment. [Figure 11] FIG. 11 is a diagram showing a specific example of the conversion process and the video generation process in the fifth embodiment. [Figure 12] FIG. 12 is a flowchart illustrating the operation of the processing circuit related to the conversion process and the video generation process in the fifth embodiment. [Figure 13] FIG. 13 is a block diagram illustrating the configuration of an image generation device according to the sixth embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0008] Hereinafter, an embodiment of a magnetic resonance imaging apparatus will be described in detail with reference to the drawings. Note that, hereinafter, elements that are the same as or similar to elements that have already been described will be assigned the same or similar reference numerals, and duplicated descriptions will generally be omitted.

[0009] In the following description, it is assumed that the image provided to the subject is projected from an image projection device onto a screen placed on a tabletop inserted into the bore of the magnetic resonance imaging device. However, the image may also be provided to the subject by being projected directly into the bore or by being displayed on a display. In other words, any configuration may be used for providing the image to the subject as long as it does not interfere with the examination.

[0010] [First embodiment] 1 is a block diagram illustrating the configuration of a magnetic resonance imaging system (MRI system) 1 including a magnetic resonance imaging apparatus (MRI apparatus) 10 according to a first embodiment. The MRI system 1 includes the MRI apparatus 10 and a video projection device 100, which are connected to each other so as to be able to communicate with each other via wire or wirelessly. The MRI apparatus 10 includes a gantry 11, a bed 13, a movable screen device 15, and an imaging control unit 17.

[0011] The bed 13 has a top plate 13a and a base 13b. The subject P is placed on the top plate 13a. The top plate 13a is supported by the base 13b so as to be movable along the X-axis, Y-axis, and Z-axis. A bed driving device 13c is housed in the base 13b. The bed driving device 13c moves the top plate 13a under control of an imaging control circuit 31 provided in the imaging control unit 17. As a result, the top plate 13a is inserted into a hollow bore 53 formed by the gantry 11. Note that a motor such as a servo motor or a stepping motor may be used as the bed driving device 13c. Furthermore, instead of the bore 53, a space corresponding to the bore 53 may be open.

[0012] The gantry 11 has a static magnetic field magnet 41, a gradient magnetic field coil 43, and an RF coil 45. The static magnetic field magnet 41 and the gradient magnetic field coil 43 are housed in a housing of the gantry 11 (hereinafter referred to as a gantry housing 51), and the RF coil 45 is disposed in a bore 53.

[0013] The static magnetic field magnet 41 has, for example, a hollow, approximately cylindrical shape and generates a static magnetic field inside the approximately cylinder. For example, a permanent magnet, a superconducting magnet, or a normal-conducting magnet is used as the static magnetic field magnet 41. Here, the central axis of the static magnetic field magnet 41 is defined as the Z-axis, the axis perpendicular to the Z-axis is called the Y-axis, and the axis horizontally perpendicular to the Z-axis is called the X-axis.

[0014] The gradient magnetic field coil 43 is a coil unit that is attached inside the static magnetic field magnet 41 and is formed, for example, in a hollow, approximately cylindrical shape. The gradient magnetic field coil 43 may be equipped with a shim coil (not shown) that corrects non-uniformity of the static magnetic field.

[0015] The imaging control unit 17 has a gradient magnetic field power supply 21, a transmission circuit 23, a reception circuit 25, an imaging control circuit 31, a processing circuit 33, a display 35, an interface 36, and a storage device 37 (storage section).

[0016] The imaging control circuit 31 is connected to the processing circuit 33, display 35, interface 36, storage device 37, gradient magnetic field power supply 21, transmission circuit 23, reception circuit 25, and gantry 11, enabling mutual communication.

[0017] The processing circuitry 33 has a processor and various memories as hardware resources. The processing circuitry 33 has various processing functions, such as a system control function 33a (controller), an acquisition function 33b (acquisition unit), a generation function 33c (generation unit), and an output control function 33d (output controller). The various processing functions, such as the system control function 33a, the acquisition function 33b, the generation function 33c, and the output control function 33d, are stored in the storage device 37 in the form of programs executable by a computer. The processing circuitry 33 is a processor that realizes the functions corresponding to each program by reading the programs corresponding to these various functions from the storage device 37 and executing them. In other words, the processing circuitry 33 in a state in which each program has been read has each function shown in the processing circuitry 33 of FIG. 1.

[0018] The processing circuitry 33 performs overall control of the MRI apparatus 10 using a system control function 33a. Specifically, the processing circuitry 33 reads a system control program stored in the storage device 37, expands it in memory, and controls each circuit of the MRI apparatus 10 according to the expanded system control program. For example, the processing circuitry 33 reads an imaging protocol from the storage device 37 using the system control function 33a based on imaging conditions input by the operator via the interface 36. The processing circuitry 33 outputs the imaging protocol to the imaging control circuit 31 in accordance with an instruction to start imaging input by the operator via the interface 36, and controls imaging. At this time, the processing circuitry 33 issues an instruction to start a desired image to the output control function 33d simultaneously with the instruction to start imaging. The imaging conditions include, for example, the type of sequence related to magnetic resonance imaging, the imaging region related to magnetic resonance imaging, and the repetition time (imaging time) of RF pulses related to magnetic resonance imaging.

[0019] The imaging control circuit 31 controls the gradient magnetic field power supply 21, the transmission circuit 23, the reception circuit 25, and the imaging control circuit 31 in accordance with the imaging protocol output from the processing circuit 33, and performs imaging of the subject P. The imaging protocol has various pulse sequences according to the examination. The imaging protocol defines the magnitude of the current supplied to the gradient magnetic field coil 43 by the gradient magnetic field power supply 21, the timing at which the gradient magnetic field power supply 21 supplies the current to the gradient magnetic field coil 43, the magnitude and time width of the RF pulse supplied to the RF coil 45 by the transmission circuit 23, the timing at which the RF pulse is supplied to the RF coil 45 by the transmission circuit 23, the timing at which the MR signal is received by the reception circuit 25, etc.

[0020] The gradient magnetic field power supply 21 supplies a current to the gradient magnetic field coil 43 under the control of the imaging control circuit 31. The gradient magnetic field power supply 21 supplies a current to the gradient magnetic field coil 43, thereby causing the gradient magnetic field coil 43 to generate a gradient magnetic field.

[0021] The RF coil 45 is disposed inside the gradient magnetic field coil 43. The RF coil 45 receives RF pulses from the transmission circuitry 23 and generates a high-frequency magnetic field. The high-frequency magnetic field generated from the RF coil 45 excites target nuclei present in the subject P at a specific resonance frequency. The RF coil 45 receives magnetic resonance signals (hereinafter referred to as MR signals) emitted from the excited target nuclei. The received MR signals are supplied to the reception circuitry 25 via a wired or wireless connection. The reception circuitry 25 processes the received MR signals to generate digital MR signals. The digital MR signals are supplied to the processing circuitry 33 via a wired or wireless connection. Although the above-mentioned RF coil 45 is a coil having a transmission and reception function, a transmission RF coil and a reception RF coil may be provided separately.

[0022] 1, it has been explained that these various functions are realized by a single processing circuit 33, but it is also possible to configure the processing circuit 33 by combining multiple independent processors, and have each processor execute a program to realize the function. In other words, it is also possible that each of the above-mentioned functions is configured as a program and one processing circuit executes each program, or that a specific function is implemented in a dedicated, independent program execution circuit.

[0023] The processing circuitry 33 may also have a reconstruction function. The reconstruction function of the processing circuitry 33 arranges the MR data along the readout direction of the k-space according to the gradient strength of the readout gradient magnetic field. The processing circuitry 33 reconstructs an MR image by performing a Fourier transform on the MR data arranged in the k-space. The processing circuitry 33 outputs the MR image to the display 35 and the storage device 37.

[0024] The display 35 displays various information, such as a reconstructed MR image.

[0025] The interface 36 includes circuits for receiving various instructions and information input from an operator. The interface 36 is realized, for example, by circuits related to a pointing device such as a mouse or an input device such as a keyboard. Note that the circuits of the interface 36 are not limited to circuits related to physical operating components such as a mouse and a keyboard. For example, examples of circuits of the interface 36 include an electrical signal processing circuit that receives electrical signals corresponding to input operations from an external input device provided separately from the MRI apparatus 10 and outputs the received electrical signals to various circuits. Note that the interface 36 may also include circuits for data communication between the image projection device 100 and external devices such as a PACS server via wired cables, wireless connections, or networks.

[0026] The storage device 37 stores MR data arranged in k-space, MR image data, image generation parameters, various images, etc. The storage device 37 stores various imaging protocols, imaging conditions including multiple imaging parameters that define the imaging protocols, etc. The storage device 37 stores programs corresponding to various functions executed by the processing circuitry 33.

[0027] The storage device 37 is, for example, a semiconductor memory element such as a random access memory (RAM), a flash memory, a hard disk drive, a solid state drive, an optical disk, etc. The storage device 37 may also be a drive that reads and writes various information from and to a portable storage medium such as a CD-ROM drive, a DVD drive, or a flash memory.

[0028] A mobile screen device 15 is provided within the bore 53 so as to be movable in an insertion direction (Z direction) in which the top plate is inserted into the bore 53. The mobile screen device 15 includes a moving body 61, a screen 63, a frame 65, and a reflecting plate 67. The moving body 61 supports the screen 63 and the frame 65. The moving body 61 is a structure (a moving cart) that is movable along rails (not shown) that are provided on the inner wall of the frame housing 51 and parallel to the central axis Z. The rails and the moving body 61 are made of a non-magnetic material that does not act on a magnetic field. Wheels (not shown) that roll on the rails are provided below the moving body 61 to improve its running performance on the rails. Note that wheels are not necessarily required as long as the moving body 61 can run on the rails; it is sufficient that the surface that comes into contact with the rails is made of a material with a low coefficient of friction.

[0029] The screen 63 is provided on the moving body 61. The image projection device 100 projects an image corresponding to data from the imaging control unit 17 onto the screen 63. Specifically, the image from the image projection device 100 is projected onto the screen 63 from the side opposite the side where the tabletop 13a is inserted into the bore 53. In other words, the image projection device 100 is disposed on the opposite side of the screen 63 from the bed 13. At least the upper half of the screen 63 has a shape similar to the cross-sectional shape of the bore 53 perpendicular to the Z axis or an elliptical shape, and is configured to a size that allows it to move within the bore 53. The lower end of the screen 63 has a shape that matches the shape of the moving body 61. Here, the surface of the screen 63 facing the image projection device 100 will be called the front side, and the surface facing the bed 13 will be called the back side.

[0030] Projection light emitted from the image projection device 100 is irradiated onto the surface of the screen 63, and an image corresponding to the projection light is projected onto the rear surface. At this time, by adjusting the position of the moving body 61 to change the positional relationship between the moving body 61 and the subject P on the tabletop 13a, the reflecting plate 67 is set in the line of sight of the subject P. This allows the subject P and the like to view the image projected onto the screen 63 through the reflecting plate 67 from the side of the bed 13. (Sound generated by magnetic resonance imaging equipment)

[0031] Generally, the noise generated during magnetic resonance imaging is caused by the vibration of the gradient coil that generates gradient magnetic fields in three orthogonal axes (X, Y, Z). Specifically, when a current is supplied from a gradient power supply to a gradient coil placed in a magnetic field, a Lorentz force acts on the gradient coil to which the current is supplied. The Lorentz force then causes minute deformation and positional displacement in the gradient coil. The noise is generated when the gradient coil vibrates in accordance with the time-dependent change in the minute deformation and positional displacement caused by the Lorentz force.

[0032] The volume of the generated sound varies depending on the value of the current supplied to the gradient magnetic field coil and the time rate of change of the supplied current value. In particular, the larger the time rate of change of the current value, the larger the change in the Lorentz force. When the change in the Lorentz force is large, the vibration of the gradient magnetic field coil increases, and the volume of the generated sound tends to increase. In other words, the volume of the generated sound varies depending on the imaging conditions.

[0033] Furthermore, the current waveform applied to the gradient magnetic field coil is not a pure sine wave, but a trapezoidal waveform or a trapezoidal waveform that partially includes a sine wave. These current waveforms differ in current peak value and other characteristics depending on the imaging conditions. In other words, the tone of the generated sound differs depending on the imaging conditions. Below, we will specifically explain the sequence (type), imaging area, and repetition time included in the imaging conditions.

[0034] A sequence is an imaging method selected depending on the purpose of imaging, such as spin echo imaging, gradient echo imaging, fast spin echo imaging, fast gradient echo imaging, and echo planar imaging. Different imaging methods have different timings for the current flowing through the gradient coil, which results in different sounds being generated.

[0035] The imaging region is determined by the slice thickness and FOV (Field Of View). The MRI apparatus 10 can select any slice cross section, such as axial, sagittal, or colonial. The selection of the imaging region changes the ratio of currents flowing through each axis of the gradient magnetic field coil, resulting in a change in the generated sound. Specifically, the smaller the slice thickness, the larger the current flowing through the gradient magnetic field coil, resulting in a louder generated sound. Furthermore, the MRI apparatus 10 increases the current flowing through the gradient magnetic field coil in inverse proportion to the size of the FOV, resulting in a louder generated sound.

[0036] The repetition time is the period for one data acquisition when the conditions for a certain sequence are changed slightly. For example, if the repetition time is 1 millisecond, a 1 kHz sound will be generated. The repetition time may also include relatively long repetition times (e.g., 500 milliseconds) such as the IR pulse repetition time and saturation pulse repetition time, which are performed as needed. In this case, the repetition time is closely related to the timing of the generated sound, which is repeated at a predetermined time period. (Image generation processing)

[0037] The processing circuitry 33 acquires patient information and examination information from a RIS (Radiology Information Systems) via the interface 36 using the acquisition function 33b in response to a user instruction. The patient information is information about a patient undergoing an examination using a medical imaging device. Specifically, the patient information includes, for example, gender, age (generation), and visual characteristics. The visual characteristics are, for example, characteristics related to visual acuity, visual field, and color vision. The examination information is information about the medical imaging device that performs the examination. Specifically, if the medical imaging device is an MRI device, the examination information includes the imaging conditions of the MRI device. The patient information may also include preference information about the patient's preferences.

[0038] The processing circuitry 33 uses the generation function 33c to generate video information suitable for the patient and the examination using a trained model based on the patient information and examination information. The trained model is configured, for example, by generative AI (generative artificial intelligence) and is trained to output video when predetermined information is input. The predetermined information is, for example, patient information and examination information. In other words, the processing circuitry 33 generates video information by inputting the patient information and examination information to the trained model. Hereinafter, the process of generating video information using the generation function 33c will be referred to as the "video generation process."

[0039] Specifically, the trained model in the first embodiment is a machine learning model trained based on, for example, a combination of gender and age included in patient information, a combination of a sequence type and imaging time included in examination information, and video information prepared in advance according to each combination. The content of the video information used for training is determined, for example, according to gender and age, and is varied according to the sequence type within the determined content. This makes it possible to generate a wide variety of video information based on patient information and examination information.

[0040] The above-mentioned video information is, for example, content that induces a patient state that allows a smooth examination. A patient state that allows a smooth examination is a state in which the patient is relaxed. Specifically, a patient in a relaxed state is a state in which the heart rate is stable (the change in heart rate is within a certain range), the breathing is stable (the number of breaths in a given time is within a certain range), and there is no or little body movement. Note that a patient state that allows a smooth examination may also be rephrased as "a patient state that is optimal for an examination."

[0041] For example, because MRI examinations generally do not allow the use of vision correction devices (e.g., glasses and contact lenses), if a myopic patient views content based on normal vision, they may be unable to understand the content and become unable to relax. Therefore, if the patient information includes visual characteristics, including the visual acuity of "myopia," the generated video information is not content that clearly defines the contours of subjects, but content that the patient can still understand even if the contours of subjects are blurred. It is believed that by having patients view content that takes such visual characteristics into account, the patient's condition can be stabilized.

[0042] Furthermore, the processing circuitry 33 may cause the generation function 33c to store, in the storage device 37, image generation parameters related to the trained model used when generating image information. The image generation parameters are, for example, instruction information (also called a prompt) that expresses, in the form of a group of words or a sentence, what kind of image to generate. In other words, the image generation parameters are information that expresses an image in the form of a group of words or a sentence. The image generation parameters may also be explanatory text (captions) for the output image information.

[0043] For example, if the desired image is a peaceful image, the prompt is a sentence that evokes a peaceful image, such as, "Under the blue sky, rice fields stretch out, and children carrying butterfly nets are walking and talking."

[0044] Furthermore, if the generation function 33c stores the patient's past image generation parameters in the storage device 37, the processing circuitry 33 may use the past image generation parameters as the initial parameters of the trained model. For example, for patients who have undergone similar examinations in the past, it is highly likely that the image generation parameters are the same to a certain extent. Therefore, when the same patient undergoes an examination again, for example, by using the image generation parameters from the previous examination as the initial parameters, it is possible to generate image information that can lead to an optimal patient condition for the examination from the start of the examination. Furthermore, the storage device 37 may store the image information generated by the processing circuitry 33. The image information stored in the storage device 37 may be associated with at least one of patient information, examination information, and image generation parameters.

[0045] The processing circuitry 33 outputs the generated video information to the video projection device 100 using the output control function 33d. The processing circuitry 33 also controls the output of the video information using the output control function 33d. As part of the output control of the video information, the processing circuitry 33 may determine the end of the output period of the video information. The determination of the end of the output period may be made, for example, based on the end time of the MRI examination. The end time of the MRI examination is based, for example, on the imaging conditions. The determination of the end of the output period may also be made, for example, based on the length of the generated video information. The display 35 may also display the video projected by the video projection device 100.

[0046] 2 is a diagram showing a specific example of image generation processing in the first embodiment. The processing circuitry 33 generates image information by executing image generation processing 200 on input information (patient information and examination information). The processing circuitry 33 also outputs image generation parameters related to the generation of the image information.

[0047] Fig. 3 is a flowchart illustrating the operation of the processing circuit related to image generation processing in the first embodiment. The flowchart in Fig. 3 is executed by the processing circuit 33 in response to execution of an image generation processing program in response to a user instruction, for example.

[0048] (Step SA1) When the image generation processing program is executed, the processing circuitry 33 acquires patient information and examination information using the acquisition function 33b.

[0049] (Step SA2) After acquiring the patient information and examination information, the processing circuitry 33 inputs the patient information and examination information into the trained model using the generation function 33c to generate image information.

[0050] (Step SA3) After generating the video information, the processing circuitry 33 outputs the generated video information to the video projection device 100 using the output control function 33d.

[0051] (Step SA4) While the video information is being output, the processing circuit 33 determines whether the output period has ended using the output control function 33d. If it is determined that the output period has not ended, the processing circuit 33 continues outputting the video information, and the process repeats step SA4 for further determination. If it is determined that the output period has ended, the processing circuit 33 ends outputting the video information, and the process proceeds to step SA5.

[0052] (Step SA5) After the output of the video information is completed, processing circuitry 33 causes generation function 33c to store the video generation parameters in storage device 37. After step SA5, the processing of the flowchart ends. Note that the video generation parameters may be stored in storage device 37 after the generated video is output to video projection device 100.

[0053] As described above, the magnetic resonance imaging apparatus according to the first embodiment acquires patient information about a patient undergoing an examination and examination information about its own apparatus (magnetic resonance imaging apparatus) that performs the examination, and generates image information suitable for the patient and the examination based on the patient information and the examination information using a trained model that is trained to output an image when predetermined information is input. In the first embodiment, the predetermined information is the patient information and the examination information.

[0054] Therefore, in the first embodiment, an image corresponding to the patient is generated, and the generated image can be projected onto the screen 63. As a result, the patient in the bore can view the image, thereby reducing the sense of anxiety and claustrophobia. Therefore, the magnetic resonance imaging apparatus according to the first embodiment can improve the imaging environment for imaging by the magnetic resonance imaging apparatus.

[0055] Furthermore, the magnetic resonance imaging apparatus according to the first embodiment can generate images for each examination, thereby increasing the variety of images provided to patients. Note that the trained model used to generate the image information may be configured by a generation AI.

[0056] [Second embodiment] The video generation process in the second embodiment will be described below, with the explanation of parts that are the same as those in the first embodiment being omitted.

[0057] In the second embodiment, the processing circuitry 33 further acquires biological information of the patient at regular time intervals (including real time) using the acquisition function 33b. The biological information is information related to the condition of the patient undergoing an examination. Specifically, the biological information includes, for example, respiration (respiratory rate), pulse (heart rate), and body movement. The biological information is also acquired by a device attached to the patient, an electrocardiograph, a camera capturing an image of the patient, and the like.

[0058] When biological information is acquired, the processing circuitry 33 may determine, using the system control function 33a, whether or not there is a change in the biological information. Specifically, the processing circuitry 33 determines whether or not there is a change in the biological information using a predetermined threshold. The predetermined threshold is, for example, the respiratory rate and heart rate at rest. When the biological information is the respiratory rate, the processing circuitry 33 determines that there is a change in the biological information when the respiratory rate exceeds the value at rest. When the biological information is the heart rate, the processing circuitry 33 determines that there is a change in the biological information when the heart rate exceeds the value at rest. For example, when there is a change in the biological information, the patient is not at rest, and therefore it can be said that the patient's condition is not optimal for testing.

[0059] In other words, the processing circuit 33 determines a change in the biological information based on a value indicating the biological information and a predetermined threshold (first threshold). The processing circuit 33 determines that there is a change in the biological information when the value indicating the biological information is greater than the first threshold. The processing circuit 33 determines that there is no change in the biological information when the value indicating the biological information is equal to or less than the first threshold. Note that the method of determining a change in the biological information is not limited to the above. The processing circuit 33 may determine that there is a change in the biological information based on an amount of change in the value indicating the biological information and a predetermined threshold (second threshold). The processing circuit 33 may determine that there is a change in the biological information when the amount of change in the value indicating the biological information is greater than the second threshold. The processing circuit 33 may determine that there is no change in the biological information when the amount of change in the value indicating the biological information is equal to or less than the second threshold. Furthermore, the processing circuit 33 may determine that there is a change in the biological information using both the first threshold and the second threshold.

[0060] Furthermore, in the second embodiment, the processing circuitry 33 generates video information suitable for the patient and the examination using a trained model based on patient information, examination information, and biological information using the generation function 33c. The trained model is, for example, configured by a generation AI and trained to output video when predetermined information is input. The predetermined information is, for example, patient information, examination information, and biological information. In other words, the processing circuitry 33 generates video information by inputting patient information, examination information, and biological information to the trained model. By inputting biological information in addition to patient information and examination information, the processing circuitry 33 can change the video information it generates, for example, when the patient is resting and at other times (for example, when excited). Note that the biological information input to the trained model may be the transition of the biological information and the degree of change in the biological information. Hereinafter, these will be collectively described as biological information.

[0061] Specifically, the trained model in the second embodiment is a machine learning model trained based on, for example, a combination of patient information, test information, and the patient's state (e.g., resting or excited) included in the biological information, and video information prepared in advance according to each combination. The video information used for training has different content depending on the patient's state. For example, if the patient is excited, the video information is a peaceful video that calms the patient. This makes it possible to generate various variations of video information based on the patient information, test information, and biological information.

[0062] 4 is a diagram showing a specific example of image generation processing in the second embodiment. The processing circuitry 33 generates image information by executing image generation processing 400 on input information (patient information and examination information) and feedback information (biological information). The processing circuitry 33 also outputs image generation parameters related to the generation of the image information.

[0063] Fig. 5 is a flowchart illustrating the operation of the processing circuit related to image generation processing in the second embodiment. The flowchart in Fig. 5 is executed by the processing circuit 33 in response to execution of an image generation processing program in response to a user instruction, for example.

[0064] (Step SB1) When the image generating program is executed, the processing circuitry 33 acquires patient information, examination information, and biological information using the acquisition function 33b.

[0065] (Step SB2) After acquiring the patient information, examination information, and biological information, the processing circuitry 33 inputs the patient information, examination information, and biological information into the trained model using the generation function 33c to generate video information.

[0066] (Step SB3) After generating the video information, the processing circuitry 33 outputs the generated video information to the video projection device 100 using the output control function 33d.

[0067] (Step SB4) While the video information is being output, the processing circuit 33 determines whether the output period has ended. If it is determined that the output period has not ended, the processing circuit 33 continues to output the video information, and the process proceeds to step SB5. If it is determined that the output period has ended, the processing circuit 33 ends the output of the video information, and the process proceeds to step SB8.

[0068] (Step SB5) After determining that the output period has not ended, the processing circuit 33 determines whether there is a change in the biometric information using the system control function 33a. If it is determined that there is a change in the biometric information, the process proceeds to step SB6. If it is determined that there is no change in the biometric information, the processing circuit 33 continues to output the video information, and the process returns to step SB4.

[0069] (Step SB6) After determining that there is a change in the biological information, the processing circuitry 33 inputs the patient information, examination information, and biological information (biological information after the change) into the trained model using the generation function 33c to regenerate (update) the video information. If there is a change in the biological information, the patient's condition is not optimal for the examination, so the processing circuitry 33 generates video information that will make the patient more relaxed than before. In other words, the video information in step SB6 is different from the video information in step SB2.

[0070] In other words, the processing circuitry 33 updates the video information by inputting the patient information, the examination information, and the biometric information to the trained model when the value indicating the biometric information (or the amount of change in the value indicating the biometric information) is greater than a predetermined threshold. On the other hand, the processing circuitry 33 does not update the video information when the value indicating the biometric information (or the amount of change in the value indicating the biometric information) is equal to or less than the predetermined threshold.

[0071] (Step SB7) After regenerating the video information, the processing circuitry 33 uses the output control function 33d to output the regenerated video information to the video projection device 100. Note that the regenerated video information may be changed in real time to seamlessly connect to the original video information.

[0072] (Step SB8) After it is determined in step SB4 that the output period has ended and the output of the video information has ended, processing circuitry 33 causes generation function 33c to store the video generation parameters in storage device 37. After step SB8, the processing of the flowchart ends. Note that the video generation parameters may also be stored in storage device 37 after the generated video is output to video projection device 100.

[0073] As described above, the magnetic resonance imaging apparatus according to the second embodiment acquires patient information about the patient undergoing the examination, examination information about the apparatus (magnetic resonance imaging apparatus) that performs the examination, and biological information about the patient, and generates image information suitable for the patient and the examination based on the patient information, examination information, and biological information using a trained model that is trained to output images when predetermined information is input. In the second embodiment, the predetermined information is the patient information, examination information, and biological information.

[0074] Therefore, in the second embodiment, in addition to patient information and examination information, biological information is also used to generate an image that corresponds to the patient. By taking the biological information into consideration, it is possible to generate an image that is more suitable for the patient and the examination. Therefore, the magnetic resonance imaging apparatus according to the second embodiment can obtain effects equal to or greater than those of the first embodiment.

[0075] Furthermore, the magnetic resonance imaging apparatus according to the second embodiment may determine whether there is a change in the biological information using a predetermined threshold, and if there is a change in the biological information, may input patient information, examination information, and biological information into the trained model to regenerate image information. In this way, the magnetic resonance imaging apparatus according to the second embodiment can generate image information that guides the patient to rest when, for example, the biological information changes from resting to excitement.

[0076] [Third embodiment] In the first and second embodiments, video information is directly generated from input information by video generation processing. On the other hand, in the third embodiment, a conversion process is performed on the input information as preprocessing of the video generation processing.

[0077] 6 is a block diagram illustrating the configuration of a processing circuit 600 of a magnetic resonance imaging apparatus according to the third embodiment. The magnetic resonance imaging apparatus according to the third embodiment includes a processing circuit 600 instead of the processing circuit 33 of FIG.

[0078] The processing circuit 600 has a processor and various memories as hardware resources. The processing circuit 600 has various processing functions such as a system control function 600a (control unit), an acquisition function 600b (acquisition unit), a conversion function 600c (conversion unit), a generation function 600d (generation unit), and an output control function 600e (output control unit). The various processing functions such as the system control function 600a, the acquisition function 600b, the conversion function 600c, the generation function 600d, and the output control function 600e are stored in the storage device 37 in the form of programs executable by a computer. The processing circuit 600 is a processor that realizes the functions corresponding to each program by reading the programs corresponding to these various functions from the storage device 37 and executing them. In other words, the processing circuit 600 in a state in which each program has been read has each function shown in the processing circuit 600 of FIG. 6.

[0079] 6, it has been explained that these various functions are realized by a single processing circuit 600, but it is also possible to configure the processing circuit 600 by combining multiple independent processors, and have each processor execute a program to realize the function. In other words, it is possible that each of the above-mentioned functions is configured as a program and one processing circuit executes each program, or that a specific function is implemented in a dedicated, independent program execution circuit.

[0080] The processing circuit 600 controls the MRI apparatus 10 in the third embodiment in an integrated manner using a system control function 600a. Note that the configuration of the system control function 600a is substantially the same as the configuration of the system control function 33a in the first embodiment, and therefore a detailed description thereof will be omitted.

[0081] The processing circuit 600 acquires patient information and examination information by an acquisition function 600b. Note that the configuration of the acquisition function 600b is substantially the same as the configuration of the acquisition function 33b in the first embodiment, and therefore a detailed description thereof will be omitted.

[0082] The processing circuit 600 converts the patient information and examination information into image generation parameters related to the trained model using the conversion function 600c. Hereinafter, the process of converting into image generation parameters using the conversion function 600c will be referred to as the "conversion process." Note that the image generation parameters of the third embodiment are the same as the image parameters described in the first embodiment.

[0083] The conversion process may use, for example, a lookup table in which patient information, examination information, and prompts are associated with each other, or a machine learning model trained using teaching data in which patient information, examination information, and prompts are associated with each other. The machine learning model may also be configured by a generation AI.

[0084] In other words, the processing circuit 600 generates image generation parameters by inputting patient information and examination information into a second learned model trained to output image generation parameters based on patient information and examination information using the conversion function 600c.

[0085] The processing circuit 600 uses the generation function 600d to generate image information suitable for the patient and the examination using a trained model based on the image generation parameters. The trained model is configured, for example, by a generation AI and is trained to output an image by inputting predetermined information. In the second embodiment, the predetermined information is, for example, the image generation parameters. In other words, the processing circuit 600 generates image information by inputting the image generation parameters to the trained model. Hereinafter, the process of generating image information using the generation function 600d will be referred to as the "image generation process."

[0086] Specifically, the trained model in the third embodiment is a machine learning model trained based on, for example, prompts constituting video generation parameters and video information prepared in advance in response to the prompts, thereby enabling the generation of various types of video information based on the content of the prompts.

[0087] Furthermore, the processing circuit 600 may cause the generation function 600d to store the image generation parameters to be input to the trained model in the storage device 37. Furthermore, if the generation function 600d stores the patient's past image generation parameters in the storage device 37, the processing circuit 600 may use the past image generation parameters as initial parameters of the trained model.

[0088] The processing circuit 600 outputs the generated video information to the video projection device 100 using the output control function 600e. The processing circuit 600 also controls the output of the video information using the output control function 600e. As part of the output control of the video information, the processing circuit 600 may determine the end of the output period of the video information.

[0089] The processing circuitry 600 may also have a reconstruction function. The reconstruction function of the processing circuitry 600 arranges the MR data along the readout direction of the k-space according to the gradient strength of the readout gradient magnetic field. The processing circuitry 600 reconstructs an MR image by performing a Fourier transform on the MR data arranged in the k-space. The processing circuitry 600 outputs the MR image to the display 35 and the storage device 37.

[0090] 7 is a diagram showing a specific example of the conversion process and image generation process in the second embodiment. The processing circuitry 600 generates image generation parameters by performing a conversion process 710 on input information (patient information and examination information). The processing circuitry 600 generates image information by performing an image generation process 720 on the image generation parameters.

[0091] Fig. 8 is a flowchart illustrating the operation of the processing circuit related to the conversion processing and video generation processing of Fig. 7. The flowchart of Fig. 8 starts, for example, when a video generation processing program is executed.

[0092] (Step SC1) When the image generation processing program is executed, the processing circuit 600 acquires patient information and examination information using the acquisition function 600b.

[0093] (Step SC2) After obtaining the patient information and examination information, the processing circuit 600 converts the patient information and examination information into image generation parameters through the conversion function 600c.

[0094] (Step SC3) After converting the patient information and examination information into image generation parameters, the processing circuit 600 inputs the image generation parameters to the trained model using the generation function 600d to generate image information.

[0095] (Step SC4) After generating the video information, the processing circuit 600 outputs the generated video information to the video projection device 100 through the output control function 600e.

[0096] (Step SC5) While the video information is being output, the processing circuit 600 determines whether the output period has ended using the output control function 600e. If it is determined that the output period has not ended, the processing circuit 600 continues outputting the video information, and the process repeats step SC5 for further determination. If it is determined that the output period has ended, the processing circuit 600 ends outputting the video information, and the process proceeds to step SC6.

[0097] (Step SC6) After the output of the video information is completed, processing circuit 600 causes generation function 600d to store the video generation parameters in storage device 37. After step SC6, the processing of the flowchart ends.

[0098] As described above, the magnetic resonance imaging apparatus of the third embodiment acquires patient information about the patient undergoing the examination and examination information about the apparatus (magnetic resonance imaging apparatus) that performs the examination, converts the patient information and examination information into image generation parameters for a trained model, and generates image information suitable for the patient and examination using the trained model that has been trained to output images by inputting the image generation parameters.

[0099] Therefore, the magnetic resonance imaging apparatus according to the third embodiment can improve the imaging environment for imaging by the magnetic resonance imaging apparatus, as in the first embodiment. Furthermore, the magnetic resonance imaging apparatus according to the third embodiment uses image generation parameters in a format that can be edited by the user, and therefore the image generation parameters can be freely edited to suit the patient.

[0100] [Fourth embodiment] The conversion process and video generation process in the fourth embodiment will be described below, with explanations of parts that are the same as those in the third embodiment being omitted.

[0101] In the fourth embodiment, the processing circuit 600 further acquires the patient's biological information at regular time intervals (including real time) using the acquisition function 600b. When the biological information is acquired, the processing circuit 600 may determine whether there is a change in the biological information using the system control function 600a.

[0102] In addition, the processing circuit 600 converts patient information, examination information, and biological information into image generation parameters for the trained model using the conversion function 600c.

[0103] The conversion process may use, for example, a lookup table in which patient information, test information, and biometric information are associated with prompts, or a machine learning model trained using training data in which patient information, test information, and biometric information are associated with prompts. The machine learning model may also be configured by a generation AI.

[0104] In other words, the processing circuit 600 generates image generation parameters by inputting patient information, examination information, and biometric information into a second machine-learned model trained to output image generation parameters based on the patient information, examination information, and biometric information using the conversion function 600c.

[0105] 9 is a diagram showing a specific example of conversion processing and image generation processing in the fourth embodiment. Processing circuitry 600 generates image generation parameters by performing conversion processing 910 on input information (patient information and examination information) and feedback information (biometric information). Processing circuitry 600 generates image information by performing image generation processing 920 on the image generation parameters.

[0106] Fig. 10 is a flowchart illustrating the operation of the processing circuit related to the conversion process and the video generation process in the fourth embodiment. The flowchart in Fig. 10 starts, for example, when a video generation processing program is executed.

[0107] (Step SD1) When the image generation program is executed, the processing circuit 600 acquires patient information, examination information, and biological information using the acquisition function 600b.

[0108] (Step SD2) After obtaining the patient information, examination information, and biological information, the processing circuit 600 converts the patient information, examination information, and biological information into image generation parameters using the conversion function 600c.

[0109] (Step SD3) After converting the patient information, examination information, and biological information into image generation parameters, the processing circuit 600 inputs the image generation parameters to the trained model using the generation function 600d to generate image information.

[0110] (Step SD4) After generating the video information, the processing circuit 600 outputs the generated video information to the video projection device 100 through the output control function 600e.

[0111] (Step SD5) While the video information is being output, the processing circuit 600 determines whether the output period has ended using the output control function 600e. If it is determined that the output period has not ended, the processing circuit 600 continues outputting the video information, and the process proceeds to step SD6. If it is determined that the output period has ended, the processing circuit 600 stops outputting the video information, and the process proceeds to step SD10.

[0112] (Step SD6) After determining that the output period has not ended, the processing circuit 600 uses the system control function 600a to determine whether there has been a change in the biometric information. If it is determined that there has been a change in the biometric information, the process proceeds to step SD7. If it is determined that there has not been a change in the biometric information, the processing circuit 600 continues to output the video information, and the process returns to step SD5.

[0113] (Step SD7) After determining that there is a change in the biological information, the processing circuit 600 uses the conversion function 600c to reconvert the patient information, examination information, and biological information (changed biological information) into image generation parameters. If there is a change in the biological information, the patient's condition is not optimal for the examination, so the processing circuit 600 generates image generation parameters that can generate image information that will make the patient more relaxed than before. In other words, the image generation parameters in step SD7 are different from the image generation parameters in step SD2.

[0114] (Step SD8) After reconverting the patient information, test information, and biological information into image generation parameters, the processing circuit 600 inputs the image generation parameters (reconverted image generation parameters) into the trained model using the generation function 600d to regenerate (update) the image information.

[0115] In other words, steps SD6, SD7, and SD8 above are performed by the processing circuit 600. When the value indicating the biological information (or the amount of change in the value indicating the biological information) is greater than a predetermined threshold, the processing circuit 600 reconverts the patient information, examination information, and biological information into image generation parameters and updates the image information based on the reconverted image generation parameters. On the other hand, when the value indicating the biological information (or the amount of change in the value indicating the biological information) is equal to or less than the predetermined threshold, the processing circuit 600 does not update the image information.

[0116] (Step SD9) After regenerating the video information, the processing circuit 600 uses the output control function 600e to output the regenerated video information to the video projection device 100. Note that the regenerated video information may be changed in real time to seamlessly connect to the original video information.

[0117] (Step SD10) After it is determined in step SD5 that the output period has ended and the output of the video information has finished, processing circuit 600 causes generation function 600d to store the video generation parameters in storage device 37. After step SD10, the processing of the flowchart ends.

[0118] Note that processing circuitry 600 does not necessarily have to regenerate the image generation parameters in step SD7. For example, processing circuitry 600 may generate new image generation parameters based on the image generation parameters in step SD2. Specifically, if the image generation parameters are a word group, processing circuitry 600 may generate new image generation parameters by estimating one or more words from the word group that caused the change in the patient's condition and excluding or replacing the estimated one or more words.

[0119] As described above, the magnetic resonance imaging apparatus of the fourth embodiment acquires patient information about the patient undergoing the examination, examination information about the apparatus (magnetic resonance imaging apparatus) performing the examination, and the patient's biometric information, converts the patient information, examination information, and biometric information into image generation parameters for a trained model, and generates image information suitable for the patient and the examination using a trained model that has been trained to output images by inputting the image generation parameters.

[0120] Therefore, the magnetic resonance imaging apparatus according to the fourth embodiment can improve the imaging environment for imaging by the magnetic resonance imaging apparatus in real time, taking into account biological information, as in the second embodiment. Furthermore, the magnetic resonance imaging apparatus according to the fourth embodiment can also freely edit image generation parameters so as to be suitable for the patient, as in the third embodiment.

[0121] [Fifth embodiment] The conversion process and video generation process in the fifth embodiment will be described below, with the explanation of parts that are the same as the configurations of the third and fourth embodiments being omitted.

[0122] In the fifth embodiment, the processing circuit 600 converts the patient information and examination information into image generation parameters for the trained model using a conversion function 600c.

[0123] Furthermore, the processing circuitry 600 uses the generation function 600d to generate image information suitable for the patient and the examination using a trained model based on the image generation parameters and the biological information. In this case, the predetermined information input to the trained model is, for example, the image generation parameters and the biological information. In other words, the processing circuitry 600 generates image information by inputting the image generation parameters and the biological information to the trained model.

[0124] Specifically, the trained model according to the fifth embodiment is a machine learning model trained based on, for example, combinations of prompts and biometric information that constitute image generation parameters and image information prepared in advance according to each combination, thereby enabling the generation of various types of image information based on the contents of the prompts and the biometric information.

[0125] 11 is a diagram showing a specific example of conversion processing and image generation processing in the fifth embodiment. The processing circuitry 600 generates image generation parameters by performing conversion processing 1110 on input information (patient information and examination information). The processing circuitry 600 generates image information by performing image generation processing 1120 on the image generation parameters and feedback information (biometric information).

[0126] Fig. 12 is a flowchart illustrating the operation of the processing circuit related to the conversion process and the video generation process in the fifth embodiment. The flowchart in Fig. 12 starts, for example, when a video generation processing program is executed.

[0127] (Step SE1) When the image generation program is executed, the processing circuit 600 acquires patient information, examination information, and biological information using the acquisition function 600b.

[0128] (Step SE2) After obtaining the patient information, examination information, and biometric information, the processing circuit 600 converts the patient information and examination information into image generation parameters using the conversion function 600c.

[0129] (Step SE3) After converting the patient information and examination information into image generation parameters, the processing circuit 600 inputs the image generation parameters and biological information into the trained model using the generation function 600d to generate image information.

[0130] (Step SE4) After generating the video information, the processing circuit 600 outputs the generated video information to the video projection device 100 through the output control function 600e.

[0131] (Step SE5) While the video information is being output, the processing circuit 600 determines whether the output period has ended using the output control function 600e. If it is determined that the output period has not ended, the processing circuit 600 continues to output the video information, and the process proceeds to step SE6. If it is determined that the output period has ended, the processing circuit 600 ends the output of the video information, and the process proceeds to step SE9.

[0132] (Step SE6) After determining that the output period has not ended, the processing circuit 600 determines whether there is a change in the biometric information using the system control function 600a. If it is determined that there is a change in the biometric information, the process proceeds to step SE7. If it is determined that there is no change in the biometric information, the processing circuit 600 continues to output the video information, and the process returns to step SE5.

[0133] (Step SE7) After determining that there is a change in the biological information, the processing circuit 600 inputs the image generation parameters and the biological information (the changed biological information) into the trained model using the generation function 600d to regenerate (update) the image information. If there is a change in the biological information, the patient's condition is not optimal for the examination, so the processing circuit 600 generates image information that will make the patient more relaxed than before. In other words, the image information in step SE7 is different from the image information in step SE3.

[0134] In other words, when the value indicating the biometric information (or the amount of change in the value indicating the biometric information) is greater than a predetermined threshold, the processing circuit 600 updates the video information by inputting the video generation parameters and the biometric information into the trained model. On the other hand, when the value indicating the biometric information (or the amount of change in the value indicating the biometric information) is equal to or less than the predetermined threshold, the processing circuit 600 does not update the video information.

[0135] (Step SE8) After regenerating the video information, the processing circuit 600 uses the output control function 600e to output the regenerated video information to the video projection device 100. Note that the regenerated video information may be changed in real time to seamlessly connect to the original video information.

[0136] (Step SE9) After it is determined in step SE5 that the output period has ended and the output of the video information has ended, processing circuit 600 causes generation function 600d to store the video generation parameters in storage device 37. After step SE9, the processing of the flowchart ends.

[0137] As described above, the magnetic resonance imaging apparatus of the fifth embodiment acquires patient information about the patient undergoing the examination, examination information about the apparatus (magnetic resonance imaging apparatus) performing the examination, and the patient's biometric information, converts the patient information and examination information into image generation parameters for a trained model, and generates image information suitable for the patient and the examination using the trained model that has been trained to output images by inputting the image generation parameters and biometric information.

[0138] Therefore, the magnetic resonance imaging apparatus according to the fifth embodiment, like the second and fourth embodiments, can improve the imaging environment for magnetic resonance imaging in real time, taking into account biological information.

[0139] [Sixth embodiment] The first to fifth embodiments have been described with respect to magnetic resonance imaging apparatuses that generate image information, whereas the sixth embodiment will be described with respect to an image generating apparatus that generates image information.

[0140] 13 is a block diagram illustrating the configuration of an image generation device 1310 according to the third embodiment. The image generation device 1310 includes a processing circuit 1311, a display 1312, an interface 1313, a storage device 1314, and a communication interface 1315.

[0141] The processing circuit 1311 has a processor and various memories as hardware resources. The processing circuit 1311 has the various processing functions described in the processing circuit 33 of the first embodiment or the various processing functions described in the processing circuit 600 of the second embodiment. These various processing functions are stored in the storage device 1314 in the form of programs executable by a computer. The processing circuit 1311 is a processor that realizes the functions corresponding to the various programs by reading the programs corresponding to the various functions from the storage device 1314 and executing them. In other words, the processing circuit 1311 in a state in which each program has been read has the various functions described above.

[0142] 13, it has been described that these various functions are realized by a single processing circuit 1311, but it is also possible to configure the processing circuit 1311 by combining multiple independent processors, and have each processor execute a program to realize the function. In other words, it is also possible that each of the above-mentioned functions is configured as a program and one processing circuit executes each program, or that a specific function is implemented in a dedicated, independent program execution circuit. It is also possible that the various functions of the processing circuit 1311 are substantially the same as those of the first and second embodiments, and therefore a detailed description thereof will be omitted.

[0143] The display 1312 displays various information, for example, video information generated by the processing circuit 1311.

[0144] The interface 1313 includes circuits for receiving various instructions and information input from an operator. The interface 36 is realized by, for example, circuits related to a pointing device such as a mouse or an input device such as a keyboard. Note that the circuits of the interface 36 are not limited to circuits related to physical operation components such as a mouse or a keyboard. For example, an example of the circuit of the interface 1313 is an electrical signal processing circuit that receives an electrical signal corresponding to an input operation from an external input device provided separately from the image generation device 1310 and outputs the received electrical signal to various circuits.

[0145] The storage device 1314 stores patient information and examination information. The storage device 1314 may also store image generation parameters. The storage device 1314 stores programs corresponding to various functions executed by the processing circuitry 1311. The storage device 1314 may also store image information generated by the processing circuitry 1311. The image information stored in the storage device 1314 may be associated with any of patient information, examination information, biological information, and image generation parameters.

[0146] The storage device 1314 is, for example, a semiconductor memory device such as a random access memory (RAM), a flash memory, a hard disk drive, a solid state drive, an optical disk, etc. The storage device 37 may also be a drive that reads and writes various information from and to a portable storage medium such as a CD-ROM drive, a DVD drive, or a flash memory.

[0147] The communication interface 1315 has a circuit for performing data communication between the medical imaging device 1320 and an external device such as a PACS server via a wired cable, wirelessly, a network, etc. For example, the image generation device 1310 acquires patient information and examination information from the medical imaging device 1320 via the communication interface 1315. The image generation device 1310 may also acquire biological information from the medical imaging device 1320 at regular time intervals (including in real time) via the communication interface 1315.

[0148] The configuration of the image generation device according to the sixth embodiment has been described above. Note that the image generation process and the like in the image generation device according to the sixth embodiment are substantially the same as those in the specific examples of the first to fifth embodiments, and therefore will not be described again.

[0149] Therefore, the image generating device of the sixth embodiment can generate image information by performing processing similar to that of any of the first to fifth embodiments, thereby improving the imaging environment for imaging using a magnetic resonance imaging device.

[0150] The term "processor" used in the above description refers to circuits such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an Application Specific Integrated Circuit (ASIC), a programmable logic device (e.g., a Simple Programmable Logic Device (SPLD), a Complex Programmable Logic Device (CPLD), and a Field Programmable Gate Array (FPGA)).

[0151] The processor realizes its functions by reading and executing a program stored in a storage device. Note that instead of storing the program in a storage device, the program may be directly embedded in the processor's circuitry. In this case, the processor realizes its functions by reading and executing the program embedded in the circuitry. In FIG. 1, the transmitter circuit 23, receiver circuit 25, and imaging control circuit 31 are also similarly configured with electronic circuits such as the processor.

[0152] According to at least one of the embodiments described above, it is possible to improve the imaging environment for magnetic resonance imaging.

[0153] Although several embodiments have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, modifications, and combinations of embodiments can be made without departing from the spirit of the invention. These embodiments and their modifications are included within the scope and spirit of the invention, as well as within the scope of the invention and its equivalents as defined in the claims. [Explanation of symbols]

[0154] 1. Magnetic Resonance Imaging System (MRI System) 10. Magnetic resonance imaging (MRI) equipment 11 Mounting stand 13 berths 13a Top plate 13b Base 13c Sleeper Drive 15 Mobile Screen Equipment 17 Imaging control unit 21 Gradient magnetic field power supply 23 Transmitting circuit 25 Receiving circuit 31 Imaging control circuit 33,600 processing circuits 33a,600a System control function 33b,600b acquisition function 33c,600d generation function 33d,600e output control function 35 Display 36 Interface 37 Storage device 41 Static magnetic field magnet 43 Gradient magnetic field coil 45 RF coil 51 Mounting case 53 Bore 61 Mobile 63 screens 65 frames 67 Reflector 100 Video projection equipment 200,400,720,920,1120 Image generation processing 600c conversion function 710,910,1110 conversion process 1310 Image generation device 1311 Processing circuit 1312 Display 1313 Interface 1314 Storage device 1315 Communication Interface 1320 Medical Imaging Equipment

Claims

1. an acquisition unit that acquires patient information about a patient undergoing imaging using a magnetic resonance imaging apparatus and examination information about conditions for the imaging; a generation unit that generates video information by inputting the patient information and the examination information into a trained model that is trained to output a video based on the patient information and the examination information; An image generating device comprising:

2. the acquisition unit acquires biological information of the patient; The trained model is trained to output the image based on the patient information, the examination information, and the patient's biological information; The generation unit generates the video information by inputting the patient information, the examination information, and the biological information to the trained model. The image generating device according to claim 1 .

3. When the value indicating the biological information is greater than a predetermined threshold, the generation unit updates the video information by inputting the patient information, the examination information, and the biological information into the trained model. The image generating device according to claim 2 .

4. the generation unit does not update the video information when the value indicating the biometric information is equal to or less than the predetermined threshold. The image generating device according to claim 3 .

5. When a change in the value indicating the biological information is greater than a predetermined threshold, the generation unit updates the video information by inputting the patient information, the examination information, and the biological information into the trained model. The image generating device according to claim 2 .

6. the generation unit does not update the video information when a change amount of the value indicating the biological information is equal to or less than the predetermined threshold. The image generating device according to claim 5 .

7. a conversion unit that converts the patient information and the examination information into image generation parameters; the learned model is trained to output the image based on the image generation parameters; The generation unit generates the video information by inputting the video generation parameters to the trained model. The image generating device according to claim 1 .

8. the image generation parameters are information that expresses the image information as a group of words or a sentence, the conversion unit generates the image generation parameters by inputting the patient information and the examination information to a second trained model that is trained to output the image generation parameters based on the patient information and the examination information. The image generating device according to claim 7.

9. the acquisition unit acquires biological information of the patient; the conversion unit converts the patient information, the examination information, and the biological information into the image generation parameters. The image generating device according to claim 7.

10. the image generation parameters are information that expresses the image information as a group of words or a sentence, the conversion unit generates the image generation parameters by inputting the patient information, the examination information, and the biological information to a second trained model that is trained to output the image generation parameters based on the patient information, the examination information, and the biological information; The image generating device according to claim 9.

11. the acquisition unit acquires biological information of the patient; the trained model is trained to output the image based on the image generation parameters and the biometric information; The generation unit generates the video information by inputting the video generation parameters and the biometric information to the trained model. The image generating device according to claim 7.

12. the image generation parameters are information that expresses the image information as a group of words or a sentence, the conversion unit generates the image generation parameters by inputting the patient information and the examination information to a second trained model that is trained to output the image generation parameters based on the patient information and the examination information. The image generating device according to claim 11.

13. The patient information includes the patient's gender and age.

13. The image generating device according to any one of claims 1 to 12.

14. The patient information includes visual characteristics of the patient, and the video information is content that takes the visual characteristics into consideration. The image generating device according to claim 13.

15. The examination information includes at least one of a type of sequence, an imaging region, and an imaging time related to imaging by the magnetic resonance imaging apparatus.

13. The image generating device according to any one of claims 1 to 12.

16. The biological information includes at least one of a respiratory rate, a heart rate, and a body movement of the patient.

12. The image generating device according to claim 2, wherein the image generating device is a display device.

17. The trained model is configured by generative AI (Artificial Intelligence), 13. The image generating device according to any one of claims 1 to 12.

18. An image generating device according to any one of claims 1 to 12; Magnetic resonance imaging equipment Equipped with The magnetic resonance imaging apparatus a bed having a top plate on which the patient is placed; a base forming a bore into which the top plate can be inserted; Equipped with A magnetic resonance imaging system in which the image information is projected into the bore.

19. The computer acquiring patient information about a patient undergoing imaging using a magnetic resonance imaging apparatus and examination information about conditions for said imaging; generating video information by inputting the patient information and the examination information into a trained model that is trained to output a video based on the patient information and the examination information; An image generation method comprising:

Images