Medical data processing device, medical image diagnostic device, medical data processing method, and medical data processing program

Abstract

To estimate a parameter used in imaging.SOLUTION: A medical data processing device according to an embodiment comprises: an acquisition unit; and a generation unit. The acquisition unit acquires medical data. The generation unit generates an imaging parameter by inputting medical data to a learned model that generates the imaging parameter of a medical image diagnostic apparatus about the medical data on the basis of the medical data.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] An embodiment of the present invention relates to a medical data processing device, a medical image diagnostic device, a medical data processing method, and a medical data processing program. [Background technology]

[0002] Conventionally, when a user performs medical imaging in a medical image diagnostic device, for example, imaging parameters at the time of shipment, imaging parameters used in the past, imaging parameters described in textbooks or papers, etc. In addition, when a medical image and an imaging parameter are associated with each other, the user can select a medical image of a desired aspect and use the imaging parameter associated with the selected medical image.

[0003] However, there are cases where imaging parameters are not associated with some medical images. In such cases, the user must input the imaging parameters. R The parameters are difficult to estimate. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2002-010135 A [Patent Document 2] Japanese Patent Application Publication No. 05-061973 [Patent Document 3] JP 2013-176409 A Summary of the Invention [Problem to be solved by the invention]

[0005] The problem to be solved by the present invention is R The aim is to estimate the parameters. [Means for solving the problem]

[0006] A medical data processing device according to an embodiment includes an acquisition unit and a generation unit. The acquisition unit acquires medical data. The generation unit generates imaging parameters by inputting the medical data to a trained model that generates imaging parameters for a medical image diagnostic device related to the medical data based on the medical data. [Brief description of the drawings]

[0007] [Figure 1] FIG. 1 is a diagram showing the configuration of a magnetic resonance imaging apparatus according to the first embodiment. [Diagram 2] FIG. 2 is a diagram showing a first example of input and output of a trained model used in the generation function of FIG. 1 and an MR imaging device as an output destination. [Diagram 3] FIG. 3 is a flowchart for explaining a series of steps including the MR imaging parameter estimation process in the first embodiment with reference to FIG. [Figure 4] FIG. 4 is a diagram showing an example of a display screen showing a reference MR image and estimated MR imaging parameters. [Diagram 5] FIG. 5 is a diagram showing an example of a display screen showing a reference MR image and an output MR image. [Figure 6] FIG. 6 is a diagram showing a second example of input and output of a trained model used in the generation function of FIG. [Figure 7] FIG. 7 is a diagram showing a third example of input and output of a trained model used in the generation function of FIG. 1. [Figure 8] FIG. 8 is a diagram showing a fourth example of input and output of a trained model used in the generation function of FIG. 1. [Figure 9] FIG. 9 is a diagram showing a fifth example of input / output of a trained model used in the generation function of FIG. 1 and a specific example of processing related to the input. [Figure 10] FIG. 10 is a diagram showing a sixth example of input and output of a trained model used in the generation function of FIG. 1. [Figure 11] FIG. 11 is a diagram showing the arrangement of an X-ray computed tomography apparatus according to the second embodiment. [Figure 12]FIG. 12 is a diagram showing a first example of input and output of a trained model used in the generation function of FIG. 11 and a CT imaging device as an output destination. [Figure 13] FIG. 13 is a diagram showing a second example of input and output of a trained model used in the generation function of FIG. 12, a CT imaging device as an output destination, and a specific example of processing related to the input. [Figure 14] FIG. 14 is a flowchart for explaining a series of steps including the CT imaging parameter estimation process in the second embodiment with reference to FIG. [Figure 15] FIG. 15 is a diagram showing the configuration of an ultrasonic diagnostic apparatus according to the third embodiment. [Figure 16] FIG. 16 is a diagram showing a first example of input and output of a trained model used in the generation function of FIG. 15 and an ultrasound imaging device as an output destination. [Figure 17] FIG. 17 is a diagram showing a second example of input and output of the trained model used in the generation function of FIG. 16, an ultrasound imaging device as an output destination, and a specific example of processing related to the input. [Figure 18] FIG. 18 is a flowchart for explaining a series of steps including the ultrasonic imaging parameter estimation process in the third embodiment with reference to FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0008] Hereinafter, embodiments of a medical data processing device and a medical image diagnostic device will be described in detail with reference to the drawings.

[0009] The medical data processing device according to the present embodiment is a computer or processor that processes medical data collected by a medical device or the like, or medical data stored in an external storage device or the like. As the medical device according to the present embodiment, a medical image diagnostic device or a bioinformation measuring device can be used. The medical image diagnostic device collects medical images by performing medical imaging on a subject using various imaging principles. Examples of the medical image diagnostic device include a magnetic resonance imaging device, an X-ray computed tomography device, an ultrasound diagnostic device, a nuclear medicine diagnostic device, an X-ray diagnostic device, an optical coherence tomograph, an optical ultrasound device, and an endoscope. The bioinformation measuring device collects waveform data related to the bioinformation of a subject using various measurement principles. Examples of the bioinformation measuring device include an automatic analyzer, an electrocardiograph, a respirometer, a blood pressure monitor, and a pulse oximeter.

[0010] The medical data according to the present embodiment includes medical image data. The medical image data is acquired from, for example, a medical image diagnostic device, a PACS (Picture Archiving and Communication System), etc., but the source of acquisition is not important. The medical image data includes magnetic resonance (MR) image data, map image data based on MR imaging, CT image data, ultrasound image data, X-ray image data, etc. The map image data will be described later. The medical image data may be in a DICOM (Digital Imaging and Communication in Medicine) format or a non-DICOM format.

[0011] Moreover, the medical data according to the present embodiment may include medical image-like image data. The medical image-like image data is, for example, image data obtained by photographing or reading a medical image that is printed, printed, or recorded on a film. Specifically, the medical image data is image data obtained by clipping medical image data, image data obtained by photographing a medical image printed on a paper surface with a camera, or image data obtained by capturing the medical image with an optical scanner. Examples of medical image-like image data include MR image-like image data, CT image-like image data, ultrasound image-like image data, and X-ray image-like image data.

[0012] Moreover, the medical data according to the present embodiment may include supplementary data related to image data. The supplementary data is, for example, known imaging parameters, DICOM data, and label data. The imaging parameters are, for example, parameters related to imaging by a medical image diagnostic device when acquiring medical image data. The DICOM data is, for example, tag data related to imaging parameters attached to medical image data in the DICOM format. The label data is, for example, data in a One-Hot Vector format in which the presence or absence of an element corresponds to "zero" or "one."

[0013] The imaging parameters may include information about the medical image diagnostic apparatus, such as information about static magnetic field strength (e.g., 1.5T, 3T, 7T) for a magnetic resonance imaging apparatus, information about the number of multi-slice rows (e.g., 64 rows, 320 rows) for an X-ray computed tomography apparatus, and information about the type of probe (e.g., convex probe, sector probe, linear probe, 3D probe) for an ultrasound diagnostic apparatus.

[0014] The medical data processing device according to the present embodiment may be a computer or processor mounted on a medical device, or may be a computer or processor separate from the medical device. For the sake of specific explanation, the medical data processing device according to the first embodiment is a computer mounted on a magnetic resonance imaging device, the medical data processing device according to the second embodiment is a computer mounted on an X-ray computed tomography device, and the medical data processing device according to the third embodiment is a computer mounted on an ultrasound diagnostic device.

[0015] (First embodiment) Fig. 1 is a diagram showing the configuration of a magnetic resonance imaging apparatus according to the first embodiment. As shown in Fig. 1, the magnetic resonance imaging apparatus 1 includes a gantry 10, a bed 30, a gradient magnetic field power supply 21, a transmission circuit 23, a reception circuit 25, a bed driving device 27, a sequence control circuit 29, and a medical data processing device 50.

[0016] The gantry 10 has a static magnetic field magnet 41 and a gradient magnetic field coil 43. The static magnetic field magnet 41 and the gradient magnetic field coil 43 are housed in a housing of the gantry 10. A bore having a hollow shape is formed in the housing of the gantry 10. A transmitting coil 45 and a receiving coil 47 are arranged in the bore of the gantry 10.

[0017] The static magnetic field magnet 41 has 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 defined as the Y axis, and the axis horizontally perpendicular to the Z axis is defined as the X axis. The X axis, the Y axis, and the Z axis form an orthogonal three-dimensional coordinate system.

[0018] The gradient coil 43 is a coil unit attached to the inside of the static magnetic field magnet 41 and formed in a hollow, approximately cylindrical shape. The gradient coil 43 generates a gradient magnetic field by receiving a current from the gradient magnetic field power supply 21. More specifically, the gradient coil 43 has three coils corresponding to the X-axis, Y-axis, and Z-axis that are orthogonal to each other. The three coils form a gradient magnetic field whose magnetic field strength changes along each of the X-axis, Y-axis, and Z-axis. The gradient magnetic fields along each of the X-axis, Y-axis, and Z-axis are synthesized to form a slice selection gradient magnetic field Gs, a phase encoding gradient magnetic field Gp, and a frequency encoding gradient magnetic field Gr that are orthogonal to each other in a desired direction. The slice selection gradient magnetic field Gs is used to arbitrarily determine an imaging section (slice). The phase encoding gradient magnetic field Gp is ​​used to change the phase of a magnetic resonance signal (hereinafter referred to as an MR signal) according to a spatial position. The frequency encoding gradient magnetic field Gr is used to change the frequency of the MR signal according to a spatial position. In the following description, the gradient direction of the slice selection gradient magnetic field Gs is the Z axis, the gradient direction of the phase encoding gradient magnetic field Gp is ​​the Y axis, and the gradient direction of the frequency encoding gradient magnetic field Gr is the X axis.

[0019] The gradient magnetic field power supply 21 supplies a current to the gradient magnetic field coil 43 in accordance with a sequence control signal from the sequence control circuit 29. 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 gradient magnetic fields along the X-axis, Y-axis, and Z-axis. The gradient magnetic field is superimposed on the static magnetic field formed by the static magnetic field magnet 41 and applied to the subject P.

[0020] The transmission coil 45 is disposed, for example, inside the gradient magnetic field coil 43, and receives a current from the transmission circuit 23 to generate a radio frequency magnetic field pulse (hereinafter referred to as an RF magnetic field pulse).

[0021] The transmission circuit 23 supplies a current to the transmission coil 45 in order to apply an RF magnetic field pulse to the subject P via the transmission coil 45 for exciting the target protons present in the subject P. The RF magnetic field pulse oscillates at a resonance frequency specific to the target protons, and excites the target protons. An MR signal is generated from the excited target protons and is detected by the reception coil 47. The transmission coil 45 is, for example, a whole-body coil (WB coil). The whole-body coil may be used as a transmission / reception coil.

[0022] The receiving coil 47 receives MR signals emitted from target protons present in the subject P under the action of an RF magnetic field pulse. The receiving coil 47 has a plurality of receiving coil elements capable of receiving MR signals. The received MR signals are supplied to the receiving circuit 25 via wire or wirelessly. Although not shown in FIG. 1, the receiving coil 47 has a plurality of receiving channels implemented in parallel. Each receiving channel has receiving coil elements that receive MR signals and amplifiers that amplify the MR signals. The MR signals are output for each receiving channel. The total number of receiving channels and the total number of receiving coil elements may be the same, or the total number of receiving channels may be greater or less than the total number of receiving coil elements.

[0023] The receiving circuit 25 receives MR signals generated from excited target protons via the receiving coil 47. The receiving circuit 25 processes the received MR signals to generate digital MR signals. The digital MR signals can be expressed in k-space defined by spatial frequencies. Therefore, hereinafter, the digital MR signals will be referred to as k-space data. The k-space data is supplied to the medical data processing device 50 via a wired or wireless connection.

[0024] The above-mentioned transmitting coil 45 and receiving coil 47 are merely examples. A transmitting / receiving coil having a transmitting function and a receiving function may be used instead of the transmitting coil 45 and the receiving coil 47. Also, the transmitting coil 45, the receiving coil 47, and the transmitting / receiving coil may be combined.

[0025] A bed 30 is installed adjacent to the gantry 10. The bed 30 has a top plate 33 and a base 31. A subject P is placed on the top plate 33. The base 31 supports the top plate 33 so that it can slide along each of the X-axis, Y-axis, and Z-axis. A bed driving device 27 is housed in the base 31. The bed driving device 27 moves the top plate 33 under the control of a sequence control circuit 29. The bed driving device 27 may include any motor, such as a servo motor or a stepping motor.

[0026] The sequence control circuit 29 has, as hardware resources, a processor such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) and memories such as a ROM (Read Only Memory) and a RAM (Random Access Memory). The sequence control circuit 29 synchronously controls the gradient magnetic field power supply 21, the transmission circuit 23, and the reception circuit 25 based on an imaging protocol determined by the processing circuit 51, etc., performs MR imaging of the subject P according to a pulse sequence corresponding to the imaging protocol, and collects k-space data regarding the subject P.

[0027] As shown in FIG. 1, the medical data processing device 50 is a computer having a processing circuit 51, a memory 52, a display 53, an input interface 54, and a communication interface 55.

[0028] The processing circuitry 51 has a processor such as a CPU as a hardware resource. The processing circuitry 51 functions as the core of the magnetic resonance imaging apparatus 1. For example, the processing circuitry 51 has an acquisition function 511, a generation function 512, an output function 513, a display control function 514, and a learning function 515 by executing various programs. Although not shown, the processing circuitry 51 has an imaging protocol setting function, an image reconstruction function, and an image processing function by executing various programs.

[0029] In the imaging protocol setting function, the processing circuitry 51 sets an imaging protocol related to magnetic resonance imaging automatically or in response to a user instruction via the input interface 54. The imaging protocol is a set of various MR imaging parameters related to magnetic resonance imaging. The MR imaging parameters will be described later.

[0030] In the image reconstruction function, the processing circuitry 51 reconstructs an MR image based on k-space data collected by various scans. Note that the reconstruction method is not particularly limited.

[0031] In the image processing function, the processing circuitry 51 performs various image processing on the MR image. For example, the processing circuitry 51 performs image processing such as volume rendering, surface rendering, pixel value projection processing, MPR (Multi-Planer Reconstruction) processing, and CPR (Curved MPR) processing.

[0032] In the acquisition function 511, the processing circuitry 51 acquires medical data from a PACS or the like in response to a user instruction. In this embodiment, the processing circuitry 51 acquires, for example, MR image data, map image data, and MR image-like image data. In addition, the processing circuitry 51 may acquire supplementary data.

[0033] In the generation function 512, the processing circuitry 51 applies the learned model to the medical data to generate imaging parameters of the medical image diagnostic device related to the medical data. In other words, the processing circuitry 51 generates the imaging parameters by inputting the medical data to a learned model that generates imaging parameters of the medical image diagnostic device related to the medical data based on the acquired medical data. The learned model is, for example, a machine learning model that is machine-learned based on medical data prepared in advance and imaging parameters of the medical image diagnostic device related to the medical data. In this embodiment, when the medical data includes medical image data, the medical image data is associated with the medical image diagnostic device. In addition, when the medical data includes medical image-like image data, the image data is associated with the medical image device that acquired the medical image.

[0034] In this embodiment, the processing circuitry 51 applies, for example, the trained model to the MR image data to generate MR imaging parameters related to the MR image data. In other words, the processing circuitry 51 generates the MR imaging parameters by inputting the MR image data to a trained model that generates MR imaging parameters of a magnetic resonance imaging device related to the MR image data based on the acquired MR image data. At this time, the trained model is, for example, a machine learning model that is trained based on the MR image data and the MR imaging parameters (MR imaging parameters of the magnetic resonance imaging device) used when the k-space data corresponding to the MR image data is acquired.

[0035] The machine learning model according to the present embodiment is typically a deep neural network (DNN), which is a multi-layer network model that mimics the neural circuits of the brain of an organism. The DNN includes a composite function with parameters that is defined by a combination of multiple adjustable functions and parameters.

[0036] In the output function 513, the processing circuitry 51 outputs the imaging parameters of the medical image diagnostic device generated by the generating function 512 to the imaging device. The imaging device is a collective term for each unit and each circuit that performs medical imaging in the medical image diagnostic device. The processing circuitry 51 may convert the imaging parameters so that they become imaging parameters corresponding to the imaging device of the output destination. The imaging device may be the same as the medical image diagnostic device. In this embodiment, the processing circuitry 51 outputs, for example, the MR imaging parameters of the magnetic resonance imaging device generated by the generating function 512 to the MR imaging device.

[0037] In the display control function 514, the processing circuitry 51 displays various information on the display 53. For example, the processing circuitry 51 displays imaging parameters of the medical image diagnostic apparatus output by the output function 513 on the display 53. In this embodiment, the processing circuitry 51 displays, for example, a reference MR image used as input data, MR imaging parameters of the magnetic resonance imaging apparatus output by the output function 513, and an MR image (output MR image) of the subject P imaged using the MR imaging parameters on the display 53.

[0038] In the learning function 515, the processing circuitry 51 generates a trained model that is machine-learned based on medical data and imaging parameters of a medical image diagnostic device related to the medical data, which are prepared in advance. For example, the processing circuitry 51 generates a trained model by supervised machine learning that uses the medical data and the imaging parameters of a medical image diagnostic device related to the medical data as training data. Note that reinforcement learning may be used in combination in the learning.

[0039] In this embodiment, the processing circuitry 51 generates a machine learning model that is machine-learned based on, for example, MR image data and MR imaging parameters related to the MR image data that are prepared in advance. For example, the processing circuitry 51 generates a trained model by supervised machine learning that uses the MR image data and the MR imaging parameters related to the MR image data as training data.

[0040] In summary, the medical data processing device acquires medical data, and generates imaging parameters for a medical image diagnostic device related to the acquired medical data by inputting the medical data into a trained model that generates the imaging parameters based on the acquired medical data. Therefore, for example, in order for a user to set optimal imaging parameters for a medical image diagnostic device, the medical data processing device can estimate the imaging parameters from medical data whose imaging parameters are unknown. The medical data includes at least image data.

[0041] The memory 52 is a storage device such as an HDD (Hard Disk Drive), an SSD (Solid State Drive), or an integrated circuit storage device that stores various information. The memory 52 may also be a drive device 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. For example, the memory 52 stores k-space data, MR image data, map image data, various programs, and the like.

[0042] The display 53 displays various information by the display control function 514. For example, the display 53 displays imaging parameters of the medical image diagnostic apparatus output by the output function 513. In this embodiment, the display 53 displays, for example, a reference MR image, MR imaging parameters, an output MR image, etc. As the display 53, for example, a CRT display, a liquid crystal display, an organic EL display, an LED display, a plasma display, or any other display known in the art can be appropriately used.

[0043] The input interface 54 includes an input device that accepts various commands from a user. Examples of the input device that can be used include a keyboard, a mouse, various switches, a touch screen, a touch pad, and the like. Note that the input device is not limited to devices that have physical operation parts such as a mouse and a keyboard. For example, an example of the input interface 54 also includes an electrical signal processing circuit that receives an electrical signal corresponding to an input operation from an external input device provided separately from the magnetic resonance imaging apparatus 1 and outputs the received electrical signal to various circuits.

[0044] The communication interface 55 is an interface that connects the magnetic resonance imaging apparatus 1 to a workstation, a PACS, a Hospital Information System (HIS), a Radiology Information System (RIS), etc. via a Local Area Network (LAN), etc. The network IF transmits and receives various information between the connected workstation, the PACS, the HIS, and the RIS.

[0045] The above configuration is an example, and is not limited thereto. For example, the sequence control circuit 29 may be incorporated in the medical data processing device 50. The sequence control circuit 29 and the processing circuit 51 may be mounted on the same board. The sequence control circuit 29, the gradient magnetic field power supply 21, the transmission circuit 23, and the reception circuit 25 may be mounted on a single control device other than the medical data processing device 50, or may be distributed and mounted on multiple devices.

[0046] An example of the magnetic resonance imaging apparatus 1 according to this embodiment will be described below.

[0047] 2 is a diagram showing a first example of input and output of the trained model used in the generation function of FIG. 1 and an imaging device to which the model is output. The processing circuitry 51 acquires MR image data using an acquisition function 511. The processing circuitry 51 applies the trained model 60 to the MR image data using a generation function 512 to generate MR imaging parameters related to the MR image data. The processing circuitry 51 outputs the MR imaging parameters to the MR imaging device 61 using an output function 513.

[0048] The MR imaging parameters are parameters related to imaging by a magnetic resonance imaging apparatus when acquiring MR image data, and may include information related to the magnetic resonance imaging apparatus.

[0049] The MR imaging parameters include, for example, the type of acquisition system, the type of acquisition method, time parameters, flip angle, imaging section, type of reconstruction, FOV, matrix size, slice thickness, number of phase encoding steps, and scan options.

[0050] The type of acquisition system includes, for example, information on static magnetic field strength and information on acquisition coils (for example, head coil, body coil). The type of acquisition method includes, for example, information on sequence types (for example, SE (Spin Echo), FSE (Fast Spin Echo), EP (Echo Planar), IR (Inversion Recovery), GRE (Gradient Echo), bSSFP (balanced Steady State Free Precession)). The time parameters include, for example, information on time parameters that define the characteristics of a pulse sequence (for example, echo time (TE), repetition time (TR)). The type of reconstruction includes, for example, information on a reconstruction method resulting from an imaging technique (for example, PI (Parallel Imaging), CS (Compressed Sensing)), information on a reconstruction method using deep learning (Deep Learning Reconstruction: DLR), and the like. The matrix size includes, for example, information on the number of samples in the XY directions of an image and information on spatial resolution. The scan options include, for example, information on settings related to individual sequences (for example, SP (Spatial Presaturation), FS (Fat Saturation), PreIR (Pre Inversion Recovery), and the number of shots).

[0051] Fig. 3 is a flowchart for explaining a series of flows including the MR imaging parameter estimation process in the first embodiment with reference to Fig. 2. The flowchart in Fig. 3 starts when the processing circuitry 51 executes the MR imaging parameter estimation program, for example, when a user inputs an instruction to start an application related to the MR imaging parameter estimation process.

[0052] (Step SA1) When the MR imaging parameter estimation program is executed, the processing circuitry 51 executes the acquisition function 511. When the acquisition function 511 is executed, the processing circuitry 51 acquires MR image data specified by the user.

[0053] (Step SA2) After acquiring the MR image data, the processing circuitry 51 executes the generation function 512. When executing the generation function 512, the processing circuitry 51 applies the learned model to the MR image data to generate MR imaging parameters.

[0054] (Step SA3) After generating the MR imaging parameters, the processing circuitry 51 executes the display control function 514. When the display control function 514 is executed, the processing circuitry 51 displays the acquired MR image data (reference MR image) and the generated MR imaging parameters (estimated MR imaging parameters) on the display 53.

[0055] 4 is a diagram showing an example of a display screen of a reference MR image and estimated MR imaging parameters. A display screen D1 includes an MR image P1 designated by a user for estimating parameters, and a table T1 which is a list of estimated MR imaging parameters.

[0056] (Step SA4) After the display screen D1 is displayed, the processing circuitry 51 presents the user with a decision as to whether or not the estimated MR imaging parameters have been modified. Specifically, the processing circuitry 51 displays a GUI (not shown) on the display screen D1 that allows the user to modify the parameters, and determines whether or not an input regarding a modification instruction by the user has been received. If there is no modification by the user, the process proceeds to step SA6, and if there is modification by the user, the process proceeds to step SA5.

[0057] (Step SA5) The processing circuitry 51 modifies the MR imaging parameters based on the modification instruction from the user. After step SA5, the process proceeds to step SA6.

[0058] It should be noted that steps SA3, SA4 and SA5 may be omitted.

[0059] (Step SA6) After the process related to the correction of the MR imaging parameters, the processing circuitry 51 executes the output function 513. When the output function 513 is executed, the processing circuitry 51 outputs the MR imaging parameters to the MR imaging apparatus. Note that the MR imaging apparatus will be described as being the same as the magnetic resonance imaging apparatus 1.

[0060] (Step SA7) After receiving the MR imaging parameters, the processing circuitry 51 executes an imaging protocol setting function. When the imaging protocol setting function is executed, the processing circuitry 51 sets an imaging protocol based on the received MR imaging parameters, and outputs the imaging protocol to the sequence control circuitry 29. The sequence control circuitry 29 executes MR imaging and generates k-space data.

[0061] (Step SA8) After the k-space data is generated, the processing circuitry 51 executes an image reconstruction function, in which the processing circuitry 51 reconstructs the generated k-space data to generate MR image data.

[0062] (Step SA9) After the MR image data is generated, the processing circuitry 51 executes the display control function 514. When the display control function 514 is executed, the processing circuitry 51 displays the MR image data acquired in step SA1 (reference MR image) and the generated MR image data (output MR image) on the display 53, and ends the MR imaging parameter estimation process.

[0063] 5 is a diagram showing an example of a display screen for a reference MR image and an output MR image. A display screen D2 includes an MR image P1 and an MR image P2 captured based on estimated MR imaging parameters.

[0064] In the flowchart of Fig. 3, the MR imaging parameter estimation process includes the imaging process, but is not limited to this. If the MR imaging parameter estimation process does not include the imaging process, the MR imaging parameter estimation process includes at least steps SA1, SA2, and SA6. Also, the display of the MR imaging parameters in step SA2 may be omitted.

[0065] In the above, the medical image data input to the trained model is described as MR image data, but this is not limited thereto. In the following Figs. 6 to 10, the medical image data input to the trained model will be described as being other than MR image data. Note that the output from the trained model is MR imaging parameters in any case. Also, Figs. 6 to 10 omit illustration of the MR imaging device to which the MR imaging parameters are output.

[0066] FIG. 6 is a diagram showing a second example of input and output of the trained model used in the generation function of FIG. 1. The processing circuit 51 applies the trained model 62 to the map image data by the generation function 512 to generate MR imaging parameters related to the map image data. The map image is, for example, an image calculated from a plurality of MR images (for example, a tumor-likeness map, a T1 map, a T2 map, an ADC map). Since imaging by a plurality of pulse sequences is required to obtain a map image, the trained model 62 is machine-learned to output MR imaging parameters corresponding to the number of pulse sequences. For example, in the case of a tumor-likeness map, the trained model 62 is machine-learned to output a set of MR imaging parameters required for each of T1W (T1 weighted), T2W (T2 weighted), FLAIR (Fluid-Attenuated Inversion Recovery), and DWI (Diffusion Weighted).

[0067] Fig. 7 is a diagram showing a third example of input and output of the trained model used in the generation function of Fig. 1. The processing circuitry 51 applies the trained model 63 to MR image-like image data by the generation function 512, and generates MR imaging parameters related to the MR image-like image data.

[0068] Although the trained models 60, 62, and 63 described above have been machine-learned using a single type of input data, this is not limiting. For example, the trained models may be machine-learned using multiple types of input data.

[0069] FIG. 8 is a diagram showing a fourth example of input and output of the trained model used in the generation function of FIG. 1. The processing circuit 51 applies the trained model 64 to the MR image data, the map image data, or the MR image-like image data, and the supplementary data (label data) for identifying the types of the multiple image data, by the generation function 512, and generates MR imaging parameters for the identified image data. Specifically, the processing circuit 51 switches between multiple models according to the types of image data based on the label data. For example, the trained model 64 has a trained model 60, a trained model 62, and a trained model 63, respectively. The processing circuit 51 switches between the trained model 60, the trained model 62, and the trained model 63, respectively, based on the label data. Note that these models may be divided into, for example, three individual models, or weighting may be switched for one model by a software switch or the like. The above label data can function as, for example, a software switch.

[0070] The label data in Fig. 8 is data that quantifies the type of image data to be input. For example, the label data is [1,0,0] when MR image data is input, [0,1,0] when map image data is input, and [0,0,1] when MR image-like image data is input. That is, the label data associates the position of the vector value with the type of image data, and indicates the presence or absence of the type by the value of the vector.

[0071] 9 is a diagram showing a fifth example of input and output of the trained model used in the generation function of FIG. 1, and a specific example of processing related to the input. In the example of FIG. 9, it is possible to estimate MR imaging parameters of an MR image printed on an article A1. Note that the trained model 67 of FIG. 9 supports input of multiple types of image data, similar to the trained model 64 of FIG. 8.

[0072] Specifically, the user reads the article A1 with the optical scanner 65 to obtain MR image-like image data P3. As preprocessing 66, the processing circuitry 51 generates label data from the obtained image data P3. The label data here is similar to the label data in FIG. 8. Then, the processing circuitry 51 applies the trained model 67 to the image data P3 and the label data by the generation function 512 to generate MR imaging parameters for the image data P3.

[0073] 10 is a diagram showing a sixth example of input and output of the trained model used in the generation function of FIG. 1. The processing circuitry 51 acquires MR image data and supplementary data (DICOM data) related to the MR image data by the acquisition function 511. The processing circuitry 51 applies the trained model 68 to the MR image data and the DICOM data related to the MR image data by the generation function 512, and generates MR imaging parameters related to the MR image data. If there is a difference between the input DICOM data and the generated MR imaging parameters, the processing circuitry 51 may change the value of the known DICOM data to the value of the MR imaging parameters when outputting the MR imaging parameters to a downstream MR imaging device.

[0074] It is desirable that the type of DICOM tag included in the DICOM data in Fig. 10 is determined in advance at the design stage. Therefore, when inputting the DICOM data to the trained model 68, the processing circuitry 51 may attach label data in one-hot vector format indicating the presence or absence of a DICOM tag included in the DICOM data to the DICOM data.

[0075] As described above, the magnetic resonance imaging apparatus according to the first embodiment acquires MR image data, and generates MR imaging parameters of the magnetic resonance imaging apparatus related to the MR image data by inputting the MR image data to a trained model that generates the MR imaging parameters based on the acquired MR image data. Therefore, for example, in order for a user to set optimal MR imaging parameters, the magnetic resonance imaging apparatus according to the present embodiment can generate MR imaging parameters to be used for MR imaging from MR image data whose MR imaging parameters are unknown. R MR imaging parameters can be estimated.

[0076] Second embodiment In the first embodiment, the medical data processing device is described as a computer mounted on a magnetic resonance imaging device. On the other hand, in the second embodiment, the medical data processing device is described as a computer mounted on an X-ray computed tomography device. In the following description, components having substantially the same functions as those in the first embodiment are given the same reference numerals and will be described repeatedly only when necessary.

[0077] Fig. 11 is a diagram showing the configuration of an X-ray computed tomography apparatus according to the second embodiment. Although a plurality of gantry 10-2 are depicted in Fig. 11 for the convenience of explanation, typically, the X-ray computed tomography apparatus 1-2 is equipped with one gantry 10-2.

[0078] As shown in FIG. 11, the X-ray computed tomography apparatus 1-2 includes a gantry 10-2, a bed 30-2, and a medical data processing device (console) 50-2. The gantry 10-2 is a scanning device having a configuration for performing X-ray CT imaging on a subject P. The bed 30-2 is a transport device for placing the subject P to be subjected to X-ray CT imaging and positioning the subject P. The medical data processing device 50-2 is a computer that controls the gantry 10-2. For example, the gantry 10-2 and the bed 30-2 are installed in an examination room, and the medical data processing device 50-2 is installed in a control room adjacent to the examination room. The gantry 10-2, the bed 30-2, and the medical data processing device 50-2 are connected to each other by wire or wirelessly so as to be able to communicate with each other.

[0079] As shown in FIG. 11, the gantry 10-2 has an X-ray tube 11, an X-ray detector 12, a rotating frame 13, an X-ray high voltage device 14, a control device 15, a wedge filter 16, a collimator 17, and a data acquisition circuit (DAS: Data Acquisition System) 18.

[0080] The X-ray tube 11 generates X-rays. Specifically, the X-ray tube 11 includes a cathode that generates thermoelectrons, an anode that generates X-rays by receiving thermoelectrons flying from the cathode, and a vacuum tube that holds the cathode and the anode. The X-ray tube 11 is connected to the X-ray high voltage device 14 via a high-voltage cable. A filament current is supplied to the cathode by the X-ray high voltage device 14. Thermoelectrons are generated from the cathode by the supply of the filament current. A tube voltage is applied between the cathode and the anode by the X-ray high voltage device 14. The application of the tube voltage causes thermoelectrons to fly from the cathode to the anode and collide with the anode, generating X-rays. The generated X-rays are irradiated onto the subject P. A tube current flows as the thermoelectrons fly from the cathode to the anode.

[0081] The X-ray detector 12 detects X-rays generated from the X-ray tube 11 and passing through the subject P, and outputs an electrical signal corresponding to the detected X-ray dose to the DAS 18. The X-ray detector 12 has a structure in which a plurality of X-ray detection element rows, each of which has a plurality of X-ray detection elements arranged in the channel direction, are arranged in the slice direction (row direction). The X-ray detector 12 is, for example, an indirect conversion type detector having a grid, a scintillator array, and an optical sensor array. The scintillator array has a plurality of scintillators. The scintillator outputs light with an amount of light corresponding to the amount of incident X-rays. The grid is arranged on the X-ray incidence surface side of the scintillator array, and has an X-ray shielding plate that absorbs scattered X-rays. The grid is sometimes called a collimator (one-dimensional collimator or two-dimensional collimator). The optical sensor array converts light from the scintillator into an electrical signal corresponding to the amount of light. For example, a photodiode is used as the optical sensor.

[0082] The rotating frame 13 is an annular frame that supports the X-ray tube 11 and the X-ray detector 12 rotatably about a rotation axis Z. Specifically, the rotating frame 13 supports the X-ray tube 11 and the X-ray detector 12 facing each other. The rotating frame 13 is supported by a fixed frame (not shown) so as to be rotatable about the rotation axis Z. The rotating frame 13 is rotated about the rotation axis Z by the control device 15, thereby rotating the X-ray tube 11 and the X-ray detector 12 about the rotation axis Z. An image field of view (FOV: Field Of View) is set in an opening 19 of the rotating frame 13.

[0083] In this embodiment, the rotation axis of the rotating frame 13 or the longitudinal direction of the top plate 33-2 of the bed 30-2 in the non-tilted state is defined as the Z direction, the direction perpendicular to the Z direction and horizontal to the floor surface is defined as the X direction, and the direction perpendicular to the Z direction and perpendicular to the floor surface is defined as the Y direction.

[0084] X-ray high voltage device 14 has a high voltage generator and an X-ray control device. The high voltage generator has electric circuits such as a transformer and a rectifier, and generates a high voltage to be applied to X-ray tube 11 and a filament current to be supplied to X-ray tube 11. The X-ray control device controls the high voltage to be applied to X-ray tube 11 and the filament current to be supplied to X-ray tube 11. The high voltage generator may be of a transformer type or an inverter type. X-ray high voltage device 14 may be provided on a rotating frame 13 in gantry 10-2, or on a fixed frame (not shown) in gantry 10-2.

[0085] The wedge filter 16 adjusts the dose of X-rays irradiated to the subject P. Specifically, the wedge filter 16 attenuates the X-rays so that the dose of X-rays irradiated from the X-ray tube 11 to the subject P has a predetermined distribution. For example, the wedge filter 16 is a metal filter formed by processing a metal such as aluminum. The wedge filter 16 is processed to have a predetermined target angle and a predetermined thickness. The wedge filter 16 is also called a bow-tie filter.

[0086] The collimator 17 limits the irradiation range of the X-rays transmitted through the wedge filter 16. The collimator 17 slidably supports multiple lead plates that block X-rays, and adjusts the shape of the slits formed by the multiple lead plates. The collimator 17 is also called an X-ray aperture.

[0087] The DAS 18 reads out an electric signal corresponding to the dose of X-rays detected by the X-ray detector 12 from the X-ray detector 12, amplifies the read electric signal, and integrates the electric signal over a view period to collect projection data having a digital value corresponding to the dose of X-rays over the view period. The DAS 18 is realized, for example, by an ASIC equipped with a circuit element capable of generating projection data. The projection data generated by the DAS 18 is transmitted by optical communication from a transmitter having a light-emitting diode (LED) provided on the rotating frame 13 to a receiver having a light-emitting diode (LED) provided on a non-rotating part (e.g., a fixed frame) of the gantry 10-2, and is transmitted from the receiver to the medical data processing device 50-2. Note that the method of transmitting the projection data from the rotating frame 13 to the non-rotating part of the gantry 10-2 is not limited to the above-mentioned optical communication, and any method of non-contact data transmission may be used.

[0088] The bed 30-2 includes a base 31-2 and a top plate 33-2. The base 31-2 is installed on the floor surface. The base 31-2 is a structure that supports a support frame so as to be movable in a direction perpendicular to the floor surface (Y direction). The support frame is a frame provided on the upper part of the base 31-2. The support frame supports the top plate 33-2 so as to be slidable along the central axis Z. The top plate 33-2 is a flexible plate-like structure on which the subject P is placed. The bed driving device is accommodated in the bed 30-2. The bed driving device is a motor or actuator that generates power to move the top plate 33-2 on which the subject P is placed. The bed driving device operates under the control of the control device 15 or the medical data processing device 50-2, etc.

[0089] The control device 15 controls the X-ray high voltage device 14, the DAS 18, and the bed 30-2 to perform X-ray CT imaging according to imaging control by the processing circuit 51. The control device 15 has a processing circuit having a CPU and the like, and a driving device such as a motor and an actuator. The processing circuit has a processor such as a CPU and a memory such as a ROM and a RAM as hardware resources. The control device 15 controls the gantry 10-2 and the bed 30-2 according to operation signals from an input interface 54 provided on the medical data processing device 50-2, the gantry 10-2, the bed 30-2, etc. For example, the control device 15 controls the rotation of the rotating frame 13, the tilt of the gantry 10-2, and the operation of the top plate 33 and the bed 30-2.

[0090] The medical data processing device 50-2 shown in FIG. 11 is a computer having a processing circuit 51, a memory 52, a display 53, an input interface 54, and a communication interface 55.

[0091] The processing circuitry 51 is, for example, a processor that functions as the core of the X-ray computed tomography apparatus 1-2. The processing circuitry 51 executes a program stored in the memory 52 to realize a function corresponding to the program. The processing circuitry 51 has, for example, an acquisition function 511, a generation function 512, an output function 513, a display control function 514, and a learning function 515. Although not shown, the processing circuitry 51 has an imaging control function, a reconstruction processing function, an image processing function, a similarity calculation function, and a weighting change function.

[0092] In the imaging control function, the processing circuitry 51 controls the X-ray high voltage device 14, the control device 15, and the DAS 18 to perform CT imaging. The processing circuitry 51 controls the X-ray high voltage device 14, the control device 15, and the DAS 18 according to a user instruction via the input interface 54 or automatically set imaging conditions (CT imaging parameters). The CT imaging parameters will be described later.

[0093] In the reconstruction processing function, the processing circuitry 51 generates a CT image based on the projection data output from the DAS 18. Specifically, the processing circuitry 51 performs preprocessing such as logarithmic conversion processing, offset correction processing, inter-channel sensitivity correction processing, and beam hardening correction on the projection data output from the DAS 18. Then, the processing circuitry 51 performs reconstruction processing using a filtered back projection method, an iterative reconstruction method, or the like on the projection data after the preprocessing to generate a CT image.

[0094] In the image processing function, the processing circuitry 51 converts the CT image generated by the reconstruction processing function into a tomographic image of an arbitrary cross section or a three-dimensional image based on an input operation received from an operator via the input interface 54.

[0095] Descriptions will be omitted for the memory 52, the display 53, the input interface 54, the communication interface 55, the acquisition function 511, the generation function 512, the output function 513, the display control function 514, and the learning function 515. The similarity calculation function and the weighting change function will be described later.

[0096] An example of the X-ray computed tomography apparatus 1-2 according to this embodiment will be described below.

[0097] Fig. 12 is a diagram showing a first example of input and output of the trained model used in the generation function of Fig. 11 and a CT imaging device as an output destination. The processing circuitry 51 acquires CT image data by an acquisition function 511. The processing circuitry 51 applies the trained model 69 to the CT image data by a generation function 512, and generates CT imaging parameters related to the CT image data. The processing circuitry 51 outputs the CT imaging parameters to the CT imaging device 70 by an output function 513.

[0098] The CT imaging parameters are parameters related to imaging by the X-ray computed tomography apparatus when acquiring CT image data, and may include information related to the X-ray computed tomography apparatus.

[0099] CT imaging parameters include, for example, dose, iterative approximation processing parameters, AI reconstruction processing parameters, FOV, matrix size, dual energy, window level / window width (WL / WW), type of collection bin, and number of multi-slice rows.

[0100] The dose includes, for example, information on the value of the tube current and the value of the tube voltage. The parameters of the iterative approximation process include, for example, information on the type of iterative approximation process (for example, the expectation maximization (EM) method, the algebraic reconstruction technique (ART) method)) and information on the blend rate. The blend rate is the synthesis ratio of the initial image and the updated image used in the iterative approximation process. The parameters of the AI ​​reconstruction process include, for example, information on the noise reduction rate. The dual energy includes, for example, information on whether or not dual energy is used.

[0101] FIG. 13 is a diagram showing a second example of input and output of the trained model used in the generation function of FIG. 12, a CT imaging device as an output destination, and a specific example of processing related to the input. In the example of FIG. 13, CT imaging parameters are generated based on reference CT image-like image data, imaging is performed based on the generated CT image parameters, and information on the CT image data generated by imaging is fed back to the generation processing of the CT imaging parameters, thereby optimizing the display of the CT image generated in real time. To summarize FIG. 13, the X-ray computed tomography apparatus 1-2 can perform feedback control in real time on the display of the CT image using the CT image data generated by CT imaging.

[0102] 13, CT image-like image data is input to the trained model 71, but the present invention is not limited to this and CT image data may be used. In addition, the trained model 71 in FIG. 13 can change the weighting of the model based on the score data and change each value of the CT imaging parameters.

[0103] Fig. 14 is a flowchart for explaining a series of flows including the CT imaging parameter estimation process in the second embodiment with reference to Fig. 13. The flowchart in Fig. 14 starts when the processing circuitry 51 executes a CT imaging parameter estimation program, triggered by, for example, inputting an instruction to start an application related to the CT imaging parameter estimation process by a user.

[0104] (Step SB1) When the CT imaging parameter estimation program is executed, the processing circuitry 51 executes the acquisition function 511. When the acquisition function 511 is executed, the processing circuitry 51 acquires CT image-like image data designated by the user.

[0105] (Step SB2) After acquiring the CT image-like image data, the processing circuitry 51 executes the generation function 512. When executing the generation function 512, the processing circuitry 51 applies the trained model 71 to the CT image-like image data to generate CT imaging parameters for the CT image-like image data.

[0106] (Step SB3) After generating the CT imaging parameters, the processing circuitry 51 executes the output function 513. When the output function 513 is executed, the processing circuitry 51 outputs the CT imaging parameters to the CT imaging device 72. Note that the CT imaging device 72 will be described as being the same as the X-ray computed tomography apparatus 1-2.

[0107] (Step SB4) After receiving the CT imaging parameters, the processing circuitry 51 executes an imaging control function. When executing the imaging control function, the processing circuitry 51 executes CT imaging using the CT imaging parameters generated in step SB2, and collects projection data.

[0108] (Step SB5) After acquiring the projection data, the processing circuitry 51 performs a reconstruction processing function in which the processing circuitry 51 reconstructs the acquired projection data to generate CT image data.

[0109] (Step SB6) After generating the CT image data, the processing circuitry 51 executes a display control function 514. When the display control function 514 is executed, the processing circuitry 51 displays the generated CT image data on the display 53.

[0110] (Step SB7) After displaying the CT image data, the processing circuitry 51 executes a similarity calculation function. When the similarity calculation function is executed, the processing circuitry 51 calculates the similarity between the CT image-like image data acquired in step SB1 and the generated CT image data. The similarity is calculated, for example, based on the feature amount of each image data.

[0111] (Step SB8) After the similarity is calculated, the processing circuit 51 judges whether the calculated similarity is greater than a threshold value. If the similarity is greater than the threshold value, the display of the CT image generated in real time is determined to be optimized, and the processing ends. If the similarity is equal to or less than the threshold value, the display of the CT image generated in real time is determined to be not optimized, and the processing proceeds to step SB9.

[0112] (Step SB9) After the process related to the determination of the similarity, the processing circuit 51 executes a weighting change function. When the weighting change function is executed, the processing circuit 51 changes the weighting of the trained model 71 based on the score data corresponding to the similarity. After step SB9, the process returns to step SB2.

[0113] In the flowchart of Fig. 14, an example of optimizing the display of a CT image generated in real time has been described, but it is not limited to real time. For example, CT imaging is performed only with the CT imaging parameters estimated initially, and the CT imaging parameters estimated from the second time onwards are used to optimize the display screen of the generated CT image. Specifically, the processing circuit 51 optimizes the display screen of the CT image data using the WL / WW included in the CT imaging parameters estimated from the second time onwards.

[0114] As described above, the X-ray computed tomography apparatus according to the second embodiment acquires CT image data, and generates CT imaging parameters of the X-ray computed tomography apparatus related to the CT image data by inputting the CT image data to a trained model that generates the CT imaging parameters based on the acquired CT image data. Therefore, for example, in order for a user to set optimal CT imaging parameters, the X-ray computed tomography apparatus according to this embodiment generates CT imaging parameters to be used for CT imaging from CT image data whose CT imaging parameters are unknown. R CT imaging parameters can be estimated.

[0115] (Third embodiment) In the second embodiment, the medical data processing device is described as a computer mounted on an X-ray computed tomography device. On the other hand, in the third embodiment, the medical data processing device is described as a computer mounted on an ultrasound diagnostic device. In the following description, components having substantially the same functions as those in the first embodiment are given the same reference numerals and will be described repeatedly only when necessary.

[0116] Fig. 15 is a diagram showing the configuration of an ultrasonic diagnostic apparatus according to the third embodiment. As shown in Fig. 15, an ultrasonic diagnostic apparatus 1-3 has an ultrasonic probe 10-3 and a medical data processing apparatus (apparatus main body) 50-3.

[0117] The ultrasonic probe 10-3 performs ultrasonic scanning on a scanning region in a living body of a patient or the like under the control of, for example, a medical data processing device 50-3. The ultrasonic probe 10-3 has, for example, a plurality of piezoelectric transducers, a matching layer, a backing material, and the like. In this embodiment, the ultrasonic probe 10-3 has, for example, a plurality of piezoelectric transducers arranged along a predetermined direction. The ultrasonic probe 10-3 is detachably connected to the medical data processing device 50-3.

[0118] The piezoelectric transducers generate ultrasonic waves according to a drive signal supplied from an ultrasonic transmission circuit 57 of the medical data processing device 50-3. This causes ultrasonic waves to be transmitted from the ultrasonic probe 10-3 to the living body. When ultrasonic waves are transmitted from the ultrasonic probe 10-3 to the living body, the transmitted ultrasonic waves are reflected one after another at discontinuous surfaces of acoustic impedance in the internal tissue of the living body, and are received as reflected wave signals by the piezoelectric transducers. The amplitude of the received reflected wave signal depends on the difference in acoustic impedance at the discontinuous surface where the ultrasonic waves are reflected. In addition, when the transmitted ultrasonic pulse is reflected by the surface of a moving blood flow or a radiation absorbing tissue spacer, the reflected wave signal undergoes a frequency shift due to the Doppler effect depending on the velocity component in the ultrasonic transmission direction of the moving body. The ultrasonic probe 10-3 receives the reflected wave signal from the living body and converts it into an electric signal. The electric signal is supplied to the medical data processing device 50-3.

[0119] 15 is a computer that generates and displays an ultrasonic image based on a reflected wave signal received by an ultrasonic probe 10-3. As shown in FIG. 15, the medical data processing device 50-3 has an ultrasonic transmission circuit 57, an ultrasonic reception circuit 56, a processing circuit 51, a memory 52, a display 53, an input interface 54, and a communication interface 55.

[0120] The ultrasonic transmission circuit 57 is a processor that supplies a drive signal to the ultrasonic probe 10-3. The ultrasonic transmission circuit 57 is realized by, for example, a trigger generation circuit, a delay circuit, and a pulser circuit. The trigger generation circuit repeatedly generates a rate pulse for forming a transmission ultrasonic wave at a predetermined rate frequency. The delay circuit provides each rate pulse generated by the trigger generation circuit with a delay time for each piezoelectric transducer required for focusing the ultrasonic waves generated from the ultrasonic probe 10-3 into a beam shape and determining the transmission directivity. The pulser circuit applies a drive signal (drive pulse) to a plurality of ultrasonic transducers provided in the ultrasonic probe 10-3 at a timing based on the rate pulse. The delay circuit arbitrarily changes the delay time provided to each rate pulse, thereby arbitrarily adjusting the transmission direction from the piezoelectric transducer surface.

[0121] The ultrasonic receiving circuit 56 is a processor that performs various processes on the reflected wave signal received by the ultrasonic probe 10-3 to generate a received signal. The ultrasonic receiving circuit 56 is realized by, for example, an amplifier circuit, an A / D converter, a reception delay circuit, an adder, and the like. The amplifier circuit amplifies the reflected wave signal received by the ultrasonic probe 10-3 for each channel and performs gain correction processing. The A / D converter converts the gain-corrected reflected wave signal into a digital signal. The reception delay circuit provides the digital signal with a delay time required to determine the reception directivity. The adder adds multiple digital signals to which a delay time has been provided. The addition process of the adder generates a received signal in which the reflection component from the direction corresponding to the reception directivity is emphasized.

[0122] The processing circuitry 51 is, for example, a processor that functions as the core of the ultrasound diagnostic device 1-3. The processing circuitry 51 executes a program stored in the memory 52 to realize a function corresponding to the program. The processing circuitry 51 has, for example, an acquisition function 511, a generation function 512, an output function 513, a display control function 514, and a learning function 515. Although not shown, the processing circuitry 51 has a B-mode processing function, a Doppler mode processing function, an image processing function, a similarity calculation function, and a weighting change function.

[0123] In the B-mode processing function, the processing circuitry 51 generates B-mode data based on the reception signal received from the ultrasonic reception circuitry 56. Specifically, the processing circuitry 51 performs, for example, envelope detection processing and logarithmic amplification processing on the reception signal received from the ultrasonic reception circuitry 56 to generate data (B-mode data) in which the signal intensity is expressed by the brightness of luminance. The generated B-mode data is stored in a RAW data memory (not shown) as data on a two-dimensional ultrasonic scanning line (raster).

[0124] In the Doppler mode processing function, the processing circuitry 51 performs frequency analysis on the received signal received from the ultrasonic receiving circuitry 56 to generate data (Doppler data) that extracts motion information based on the Doppler effect of blood flow within a ROI (Region Of Interest) set in the scan region. Specifically, the processing circuitry 51 generates Doppler data that estimates average velocity, average variance, average power value, etc., at each of a plurality of sample points as motion information of blood flow. The generated Doppler data is stored in a RAW data memory (not shown) as data on a two-dimensional ultrasonic scan line.

[0125] In addition, the processing circuitry 51 can execute a color Doppler method called a color flow mapping (CFM) method in the Doppler mode processing function. In the CFM method, ultrasonic waves are transmitted and received multiple times on multiple scanning lines. The processing circuitry 51 applies an MTI (Moving Target Indicator) filter to a data sequence at the same position to suppress signals (clutter signals) originating from stationary tissue or slow-moving tissue and extract signals originating from blood flow. Then, the processing circuitry 51 estimates information such as the speed, variance, or power of the blood flow from the extracted signals.

[0126] In the image processing function, the processing circuitry 51 generates various types of ultrasound image data based on data generated by the B-mode processing function and the Doppler processing function. Specifically, the processing circuitry 51 generates B-mode image data composed of pixels by, for example, executing RAW-pixel conversion on the B-mode RAW data stored in the RAW data memory, for example, coordinate conversion according to the scanning form of the ultrasound by the ultrasound probe 10-3.

[0127] In addition, in the image processing function, the processing circuit 51 performs image processing such as RAW-pixel conversion on the Doppler RAW data stored in the RAW data memory to generate Doppler image data in which blood flow information is visualized. The Doppler image data is velocity image data, variance image data, power image data, or image data combining these. Note that the Doppler image data generated from the Doppler data acquired by the color Doppler method may be called color Doppler ultrasound image data.

[0128] Descriptions will be omitted for the memory 52, the display 53, the input interface 54, the communication interface 55, the acquisition function 511, the generation function 512, the output function 513, the display control function 514, and the learning function 515. The similarity calculation function and the weighting change function will be described later.

[0129] An example of the ultrasonic diagnostic apparatus 1-3 according to this embodiment will be described below.

[0130] Fig. 16 is a diagram showing a first example of input and output of the trained model used in the generation function of Fig. 15 and an ultrasound imaging device to which the data is output. The processing circuitry 51 acquires ultrasound image data using an acquisition function 511. The processing circuitry 51 applies the trained model 73 to the ultrasound image data using a generation function 512 to generate ultrasound imaging parameters related to the ultrasound data. The processing circuitry 51 outputs the ultrasound imaging parameters to the ultrasound imaging device 74 using an output function 513.

[0131] The ultrasound imaging parameters are parameters related to imaging by an ultrasound diagnostic apparatus when acquiring ultrasound image data, and may include information related to the ultrasound diagnostic apparatus.

[0132] The ultrasound imaging parameters include, for example, the type of probe, the frame rate, the dynamic range, the frequency, the flow velocity range, etc. The frequency includes, for example, information on the center frequency of the transmission signal, etc. The flow velocity range includes, for example, information on the flow velocity range in color Doppler display, etc.

[0133] Fig. 17 is a diagram showing a second example of input and output of the trained model used in the generation function of Fig. 16, an ultrasound imaging device as an output destination, and a specific example of processing related to the input. In the example of Fig. 17, ultrasound imaging parameters are generated based on image data similar to a reference color Doppler ultrasound image, imaging is performed based on the generated ultrasound imaging parameters, and information on the ultrasound image data generated by imaging is fed back to the generation processing of the ultrasound imaging parameters, thereby optimizing the display of the ultrasound image generated in real time. To summarize Fig. 17, the ultrasound diagnostic device 1-3 can perform feedback control in real time on the display of the ultrasound image using the ultrasound image data generated by ultrasound imaging.

[0134] 17, image data similar to a color Doppler ultrasound image is input to the trained model 75, but this is not limiting and color Doppler ultrasound image data may also be used. Furthermore, the trained model 75 in FIG. 17 can change the weighting of the model based on the score data and change each value of the ultrasound imaging parameters.

[0135] Fig. 18 is a flowchart for explaining a series of flows including the ultrasonic imaging parameter estimation process in the third embodiment with reference to Fig. 17. The flowchart in Fig. 18 starts when the processing circuitry 51 executes an ultrasonic imaging parameter estimation program, triggered by, for example, inputting an instruction to start an application related to the ultrasonic imaging parameter estimation process by a user.

[0136] (Step SC1) When the ultrasound imaging parameter estimation program is executed, the processing circuitry 51 executes the acquisition function 511. When the acquisition function 511 is executed, the processing circuitry 51 acquires image data like a color Doppler ultrasound image specified by the user.

[0137] (Step SC2) After acquiring the color Doppler ultrasound image-like image data, the processing circuitry 51 executes the generation function 512. When the generation function 512 is executed, the processing circuitry 51 applies the trained model 75 to the color Doppler ultrasound image-like image data to generate ultrasound imaging parameters related to the color Doppler ultrasound image-like image data. Note that the ultrasound imaging parameters include a flow velocity range.

[0138] (Step SC3) After generating the ultrasonic imaging parameters, the processing circuitry 51 executes the output function 513. When the output function 513 is executed, the processing circuitry 51 outputs the ultrasonic imaging parameters to the ultrasonic imaging device 76. Note that the ultrasonic imaging device 76 will be described as being the same as the ultrasonic diagnostic device 1-3.

[0139] (Step SC4) After receiving the ultrasonic imaging parameters, the processing circuitry 51 executes an imaging control function. When the imaging control function is executed, the processing circuitry 51 executes ultrasonic imaging using the ultrasonic imaging parameters generated in step SC2, and acquires a received signal.

[0140] (Step SC5) After acquiring the received signal, the processing circuitry 51 executes a Doppler mode processing function, in which the processing circuitry 51 performs a frequency analysis of the acquired received signal to generate Doppler data.

[0141] (Step SC6) After generating the Doppler data, the processing circuitry 51 executes an image processing function, in which the processing circuitry 51 generates color Doppler ultrasound image data by image processing the generated Doppler data.

[0142] (Step SC7) After generating the color Doppler ultrasound image data, the processing circuitry 51 executes a display control function 514. When the display control function 514 is executed, the processing circuitry 51 displays the generated color Doppler ultrasound image data on the display 53. The processing circuitry 51 also displays the color Doppler ultrasound image data based on a flow velocity range included in the ultrasound imaging parameters.

[0143] (Step SC8) After displaying the color Doppler ultrasound image data, the processing circuitry 51 executes a similarity calculation function. When the similarity calculation function is executed, the processing circuitry 51 calculates the similarity between the color Doppler ultrasound image data-like image data acquired in step SC1 and the generated color Doppler ultrasound image data.

[0144] (Step SC9) After the similarity is calculated, the processing circuit 51 determines whether the calculated similarity is greater than a threshold value. If the similarity is greater than the threshold value, the display of the color Doppler ultrasound image generated in real time is determined to be optimized, and the processing ends. If the similarity is equal to or less than the threshold value, the display of the color Doppler ultrasound image generated in real time is determined to be not optimized, and the processing proceeds to step SC10.

[0145] (Step SC10) After the process related to the similarity determination, the processing circuit 51 executes a weighting change function. When the weighting change function is executed, the processing circuit 51 changes the weighting of the trained model 75 based on the score data corresponding to the similarity. After step SC10, the process returns to step SC2.

[0146] As described above, the ultrasound diagnostic device according to the third embodiment acquires ultrasound image data, and generates ultrasound imaging parameters of the ultrasound diagnostic device related to the ultrasound image data by inputting the ultrasound image data to a trained model that generates ultrasound imaging parameters of the ultrasound diagnostic device related to the ultrasound image data based on the acquired ultrasound image data. Therefore, for example, in order for a user to set optimal ultrasound imaging parameters, the ultrasound diagnostic device according to the present embodiment can generate ultrasound imaging parameters to be used for ultrasound imaging from unknown ultrasound image data. R Ultrasound imaging parameters can be estimated.

[0147] The estimation of various imaging parameters can also be used for indexing of medical data. As an example, consider a situation where a large amount of medical data is stored in storage (e.g. SSD, HDD, cloud storage). If the medical data is data captured with various imaging parameters, users often request to search only related medical data according to their purpose. In order to efficiently refer to such medical data, a process called indexing is often performed in which additional information such as imaging parameters is added to the medical data in advance. By adding parameters estimated using the estimation of imaging parameters to the medical data stored in the storage, when a user makes a search request, it becomes possible to output related medical data while referring to the estimated parameters. Furthermore, indexing images on websites and images from papers using the estimation of various imaging parameters also enables large-scale searches of related medical data.

[0148] In addition, by using various imaging parameter estimations for medical data that is not in DICOM format, such as images from indexing websites or images from research papers, and outputting the results in DICOM format, it is possible to import the data in a searchable form into a workstation that has a search function that supports DICOM format medical data.

[0149] According to at least one of the embodiments described above, optimal imaging parameters can be set.

[0150] Although some embodiments of the present invention 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, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included in the scope of the invention and its equivalents described in the claims, as well as in the scope and spirit of the invention. [Explanation of symbols]

[0151] 1. Magnetic resonance imaging device 10,10-2 Mounting stand 30,30-2 berth 31,31-2 Foundation 33,33-2 Tabletop 41 Static magnetic field magnet 43 Gradient magnetic field coil 45 Transmitting coil 47 Receiving coil 50, 50-2, 50-3 Medical data processing device 51 Processing circuit 511 Acquisition Function 512 Generation function 513 Output Function 514 Display control function 515 Learning Function A1 Article D1,D2 display screen P1, P2 MR images P3 Image data 1-2 X-ray computed tomography equipment 11 X-ray tube 12 X-ray detector 13 Rotating Frame 14 High voltage X-ray device 16 Wedge Filter 17 Collimator 19 Opening 1-3 Ultrasound diagnostic equipment

Claims

1. An acquisition unit that acquires first medical data; a generation unit that generates imaging parameters of a medical image diagnostic device when acquiring medical data corresponding to the first medical data by inputting the first medical data into a trained model trained using second medical data and imaging parameters of a medical image diagnostic device corresponding to the second medical data; A medical data processing device comprising:

2. The first medical data is obtained by imaging parameters of the medical image diagnostic apparatus that are unknown. The medical data processing device according to claim 1 .

3. The medical image diagnostic device is any one of a magnetic resonance imaging device, an X-ray computed tomography device, an ultrasound diagnostic device, a nuclear medicine diagnostic device, an X-ray diagnostic device, an optical coherence tomography device, an optical ultrasound device, and an endoscope.

3. The medical data processing device according to claim 1.

4. the first medical data includes medical image data; The generation unit generates the imaging parameters by inputting the medical image data to the trained model that generates the imaging parameters related to the medical image data based on the medical image data. The medical data processing device according to any one of claims 1 to 3.

5. The first medical data includes medical image data and supplemental data having a portion of parameters related to the medical image data; The generation unit generates the imaging parameters by inputting the medical image data and the supplementary data to the trained model that generates the imaging parameters related to the medical image data based on the medical image data and the supplementary data. The medical data processing device according to any one of claims 1 to 4.

6. The supplemental data is known imaging parameters related to the medical image data. The medical data processing device according to claim 5 .

7. The supplemental data includes information regarding the medical imaging diagnostic device. The medical data processing device according to claim 5 .

8. The supplementary data is Digital Imaging and Communication in Medicine (DICOM) data. The medical data processing device according to claim 5 .

9. The first medical data includes medical image data and label data having information regarding a type of the medical image data; The generation unit generates the imaging parameters by inputting the medical image data and the label data to the trained model that generates the imaging parameters related to the medical image data based on the medical image data and the label data. The medical data processing device according to any one of claims 1 to 3.

10. The medical image data is associated with the medical image diagnostic apparatus. The medical data processing device according to any one of claims 4 to 9.

11. The first medical data includes medical image-like image data obtained by photographing or reading a medical image recorded on a print, printout, or film, 3. The medical data processing device according to claim 1.

12. The image data is associated with the medical image diagnostic device. The medical data processing device according to claim 11.

13. The medical image data is acquired from a magnetic resonance imaging apparatus; The imaging parameters are parameters related to the magnetic resonance imaging apparatus. The medical data processing device according to any one of claims 4 to 10.

14. The medical image data is magnetic resonance image data. The medical data processing device according to claim 13.

15. The imaging parameters include a sequence of the magnetic resonance imaging apparatus. The medical data processing device according to claim 13.

16. The first medical data includes map image data generated based on a plurality of medical image data; The generation unit generates a plurality of imaging parameters related to the plurality of medical image data by inputting the map image data to the trained model that generates the plurality of imaging parameters based on the map image data. The medical data processing device according to any one of claims 1 to 3.

17. A medical data processing device according to any one of claims 1 to 16, an imaging unit that performs medical imaging based on the imaging parameters; A medical image diagnostic apparatus comprising:

18. The medical image diagnostic apparatus according to claim 17 , wherein feedback control is performed in real time using the medical data generated by the medical imaging.

19. The computer Obtaining first medical data; generating imaging parameters of the medical image diagnostic device when acquiring medical data corresponding to the first medical data by inputting the first medical data into a trained model trained using second medical data and imaging parameters of the medical image diagnostic device corresponding to the second medical data; A medical data processing method comprising:

20. Computer, A means for acquiring first medical data; A means for generating imaging parameters of a medical image diagnostic device when acquiring medical data corresponding to the first medical data by inputting the first medical data into a trained model trained using second medical data and imaging parameters of a medical image diagnostic device corresponding to the second medical data. A medical data processing program that functions as a

Images