JP2021029479A - Learned model generation method and medical processor - Google Patents

Abstract

To obtain an image of high quality where influences by a specific substance has been reduced.SOLUTION: A generation method of a learned model according to the embodiment includes a first acquisition step, a second acquisition step and a learning step. The first acquisition step acquires a plurality of data sets corresponding to a plurality of X-ray energies obtained by X-ray scanning of an object including a specific substance. The second acquisition step acquires a single data set obtained by X-ray scanning of an object including no specific substance. The learning step deals with a plurality of X-ray energies obtained by X-ray scanning of the object including the specific substance by learning with the plurality of data sets as input and the single data set as output, and generates a learned model for generating a single data set different from the single data set where influences by the specific substance are reduced by inputting a plurality of data sets different from the plurality of data sets.SELECTED DRAWING: Figure 1

Description

Embodiments of the present invention relate to a method of generating a trained model and a medical processing device.

Conventionally, a technique called Dual Energy Scan has been used in an X-ray CT (Computed Tomography) apparatus. In this dual energy scan, image data is generated based on the change in CT value when the subject is irradiated with low-energy X-rays and high-energy X-rays. Further, there is known a method of removing a specific substance (for example, a contrast medium component, a calcium component, etc.) from the image data generated by such a dual energy scan by calculation.

However, when a specific substance is calculated and removed from the original image data by a conventional method, an unnatural part remains at the edge of the portion containing the specific substance in the original image data, and the final result is obtained. The quality of the image may deteriorate.

U.S. Pat. No. 9247919

The problem to be solved by the present invention is to obtain a high-quality image in which the influence of a specific substance is reduced.

The method of generating the trained model of the embodiment includes a first acquisition step, a second acquisition step, and a learning step. The first acquisition step acquires a plurality of data sets corresponding to a plurality of X-ray energies obtained by performing an X-ray scan on an object containing a specific substance. The second acquisition step acquires a single data set obtained by performing an X-ray scan on the object that does not contain the specific substance. The learning step is obtained by performing an X-ray scan on a subject containing the specific substance by learning using the plurality of data sets as inputs and the single data set as an output. By inputting a plurality of data sets different from the plurality of data sets corresponding to the X-ray energy of the above, the influence of the specific substance is reduced, a single data set different from the single data set. Generate a trained model to generate the dataset.

The block diagram of the X-ray CT apparatus 1 which concerns on 1st Embodiment. The figure which shows an example of the data stored in the memory 41 which concerns on 1st Embodiment. The figure which shows an example of the reconstructed image 41-4 stored in the memory 41 which concerns on 1st Embodiment. The figure which shows an example of the functional structure of the generation function 57 which concerns on 1st Embodiment. The figure which shows an example of the functional structure of the learning function 58 which concerns on 1st Embodiment. The flowchart which shows the series flow of the learning process of the processing circuit 50 which concerns on 1st Embodiment. The figure which shows the relationship between the model input and the output in the learning process of the processing circuit 50 which concerns on 1st Embodiment. The flowchart which shows the series flow of the generation processing by the processing circuit 50 which concerns on 1st Embodiment. The figure which shows an example of the data stored in the memory 41 which concerns on 2nd Embodiment. The figure which shows an example of the detection data 41-2 stored in the memory 41 which concerns on 2nd Embodiment. The flowchart which shows the series flow of the learning process of the processing circuit 50 which concerns on 2nd Embodiment. The figure which shows the relationship between the model input and output in the learning process of the processing circuit 50 which concerns on 2nd Embodiment. The flowchart which shows the series flow of the generation processing by the processing circuit 50 which concerns on 2nd Embodiment. The figure which shows another example of the relationship between the model input and output in the learning process of the processing circuit 50 which concerns on 2nd Embodiment. The figure which shows an example of the data stored in the memory 41 which concerns on 3rd Embodiment. The figure which shows an example of the reconstructed image 41-4 stored in the memory 41 which concerns on 3rd Embodiment. The flowchart which shows the series flow of the learning process of the processing circuit 50 which concerns on 3rd Embodiment. The figure which shows the relationship between the model input and the output in the learning process of the processing circuit 50 which concerns on 3rd Embodiment. The flowchart which shows the series flow of the generation processing by the processing circuit 50 which concerns on 3rd Embodiment.

Hereinafter, a method of generating the trained model of the embodiment and a medical processing apparatus will be described with reference to the drawings. The medical processing device is, for example, a medical diagnostic device that performs processing on a medical image such as an X-ray CT device to diagnose a subject. In the following description, a case where the medical processing device is an X-ray CT device will be described as an example.

(First Embodiment)
FIG. 1 is a block diagram of the X-ray CT apparatus 1 according to the first embodiment. The X-ray CT apparatus 1 executes an X-ray scan (dual energy scan). In the dual energy scan, for example, by switching the tube voltage applied to the X-ray tube using one X-ray tube, each of the low-energy X-ray and the high-energy X-ray is individually subjected to the subject. There are a method of irradiating the subject and a method of irradiating the subject with low-energy X-rays and high-energy X-rays at almost the same time while switching the tube voltage of the X-ray tube at high speed. The X-ray CT apparatus 1 may perform any type of dual energy scan.

Further, the X-ray CT apparatus 1 generates a virtual non-contrast image (hereinafter referred to as "VNC") in the image processing after the dual energy scan. This VNC is a technique for generating non-contrast imaging data by removing the contrast agent component by calculation from the imaging data of the subject to which the contrast agent is administered.

The X-ray CT device 1 includes, for example, a gantry device 10, a sleeper device 30, and a console device 40. In FIG. 1, for convenience of explanation, both a view of the gantry device 10 from the Z-axis direction and a view from the X-axis direction are shown, but in reality, the gantry device 10 is one. In the present embodiment, the rotation axis of the rotation frame 17 in the non-tilt state or the longitudinal direction of the top plate 33 of the sleeper device 30 is orthogonal to the Z-axis direction and the Z-axis direction, and the axis horizontal to the floor surface is X. The directions orthogonal to the axial direction and the Z-axis direction and perpendicular to the floor surface are defined as the Y-axis directions, respectively. The X-ray CT device 1 or the console device 40 is an example of a “medical processing device”.

The gantry device 10 includes, for example, an X-ray tube 11, a wedge 12, a collimator 13, an X-ray high voltage device 14, an X-ray detector 15, and a data acquisition system (hereinafter, DAS: Data Acquisition System) 16. , A rotating frame 17 and a control device 18.

The X-ray tube 11 generates X-rays by irradiating thermoelectrons from the cathode (filament) toward the anode (target) by applying a high voltage from the X-ray high voltage device 14. The X-ray tube 11 includes a vacuum tube. For example, the X-ray tube 11 is a rotating anode type X-ray tube that generates X-rays by irradiating a rotating anode with thermoelectrons.

The wedge 12 is a filter for adjusting the X-ray dose applied to the subject P from the X-ray tube 11. The wedge 12 attenuates the X-rays passing through itself so that the distribution of the X-ray dose radiated from the X-ray tube 11 to the subject P becomes a predetermined distribution. The wedge 12 is also called a wedge filter or a bow-tie filter. The wedge 12 is made of aluminum processed so as to have a predetermined target angle and a predetermined thickness, for example.

The collimator 13 is a mechanism for narrowing down the irradiation range of X-rays transmitted through the wedge 12. The collimator 13 narrows down the X-ray irradiation range by forming a slit, for example, by combining a plurality of lead plates. The collimator 13 is sometimes called an X-ray diaphragm.

The X-ray high voltage device 14 includes, for example, a high voltage generator and an X-ray control device. The high voltage generator has an electric circuit including a transformer, a rectifier, and the like. The high voltage generator generates a high voltage applied to the X-ray tube 11. The X-ray control device controls the output voltage of the high voltage generator according to the X-ray dose to be generated in the X-ray tube 11. The high voltage generator may be one that boosts the voltage by the transformer described above, or may be one that boosts the voltage by an inverter. The X-ray high voltage device 14 may be provided on the rotating frame 17 or may be provided on the side of the fixed frame (not shown) of the gantry device 10.

The X-ray controller controls the output voltage of the high voltage generator so that the voltage required to perform the dual energy scan is applied to the X-ray tube 11. For example, the X-ray control device follows a tube voltage control signal from the console device 40 and sends a high-energy X-ray (High-kV) (first energy X-ray) and a low-energy X-ray to the high-voltage generator. It controls which of (Low-kV) (X-ray of the second energy lower than the first energy) is output.

The X-ray detector 15 detects the intensity of X-rays generated by the X-ray tube 11 and passed through the subject P to be incident. The X-ray detector 15 outputs an electric signal (or an optical signal or the like) according to the intensity of the detected X-ray to the DAS 16. The X-ray detector 15 has, for example, a plurality of X-ray detection element sequences. Each of the plurality of X-ray detection element sequences is an array of a plurality of X-ray detection elements in the channel direction along an arc centered on the focal point of the X-ray tube 11. The plurality of X-ray detection element sequences are arranged in the slice direction (column direction, row direction).

The X-ray detector 15 is, for example, an indirect detector having a grid, a scintillator array, and an optical sensor array. The scintillator array has a plurality of scintillators. Each scintillator has a scintillator crystal. The scintillator crystal emits an amount of light according to the intensity of the incident X-rays. The grid is arranged on the surface of the scintillator array where X-rays are incident, and has an X-ray shielding plate having a function of absorbing scattered X-rays. The grid may also be called a collimator (one-dimensional collimator or two-dimensional collimator). The optical sensor array includes, for example, an optical sensor such as a photomultiplier tube (PMT). The optical sensor array outputs an electric signal according to the amount of light emitted by the scintillator. The X-ray detector 15 may be a direct conversion type detector having a semiconductor element that converts incident X-rays into an electric signal.

The DAS 16 has, for example, an amplifier, an integrator, and an A / D converter. The amplifier performs amplification processing on the electric signal output by each X-ray detection element of the X-ray detector 15. The integrator integrates the amplified electrical signal over the view period (described later). The A / D converter converts an electric signal indicating the integration result into a digital signal. The DAS 16 outputs the detection data based on the digital signal to the console device 40. The detection data is a digital value of the X-ray intensity identified by the channel number, the column number, and the view number indicating the collected view of the X-ray detection element of the generation source. The view number is a number that changes according to the rotation of the rotation frame 17, for example, a number that is incremented according to the rotation of the rotation frame 17. Therefore, the view number is information indicating the rotation angle of the X-ray tube 11. The view period is a period within a period from the rotation angle corresponding to a certain view number to the rotation angle corresponding to the next view number. The DAS 16 may detect the switching of the view by a timing signal input from the control device 18, may be detected by an internal timer, or may be detected by a signal acquired from a sensor (not shown). .. When X-rays are continuously exposed by the X-ray tube 11 in the case of performing a full scan, the DAS 16 collects a detection data group for the entire circumference (360 degrees). When X-rays are continuously exposed by the X-ray tube 11 in the case of performing a half scan, the DAS 16 collects detection data for a half circumference (180 degrees).

The rotating frame 17 is an annular member that supports the X-ray tube 11, the wedge 12, the collimator 13, and the X-ray detector 15 so as to face each other. The rotating frame 17 is rotatably supported by the fixed frame around the subject P introduced inside. The rotating frame 17 further supports the DAS 16. The detection data output by the DAS 16 has a photodiode provided in a non-rotating portion (for example, a fixed frame) of the gantry device 10 by optical communication from a transmitter having a light emitting diode (LED) provided in the rotating frame 17. It is transmitted to the receiver and transferred to the console device 40 by the receiver. The method of transmitting the detection data from the rotating frame 17 to the non-rotating portion is not limited to the method using the optical communication described above, and any non-contact type transmitting method may be adopted. The rotating frame 17 is not limited to an annular member as long as it can support and rotate the X-ray tube 11 and the like, and may be a member such as an arm.

The X-ray CT apparatus 1 is, for example, a Rotate / Rotate-Type X-ray CT apparatus (third) in which both the X-ray tube 11 and the X-ray detector 15 are supported by the rotating frame 17 and rotate around the subject P. Generation CT), but not limited to this, in Stationary / Rotate-Type in which a plurality of X-ray detection elements arranged in an annular shape are fixed to a fixed frame and the X-ray tube 11 rotates around the subject P. It may be an X-ray CT apparatus (4th generation CT).

The control device 18 includes, for example, a processing circuit having a processor such as a CPU (Central Processing Unit) and a drive mechanism including a motor, an actuator, and the like. The control device 18 receives an input signal from the input interface 43 attached to the console device 40 or the gantry device 10 and controls the operation of the gantry device 10 and the sleeper device 30.

The control device 18 rotates, for example, the rotating frame 17, tilts the gantry device 10, and moves the top plate 33 of the sleeper device 30. When tilting the gantry device 10, the control device 18 rotates the rotating frame 17 around an axis parallel to the Z-axis direction based on the tilt angle (tilt angle) input to the input interface 43. The control device 18 grasps the rotation angle of the rotation frame 17 by the output of a sensor (not shown) or the like. Further, the control device 18 provides the processing circuit 50 with the rotation angle of the rotation frame 17 at any time. The control device 18 may be provided in the gantry device 10 or in the console device 40.

The sleeper device 30 is a device on which the subject P to be scanned is placed, moved, and introduced into the rotating frame 17 of the gantry device 10. The sleeper device 30 includes, for example, a base 31, a sleeper drive device 32, a top plate 33, and a support frame 34. The base 31 includes a housing that movably supports the support frame 34 in the vertical direction (Y-axis direction). The sleeper drive device 32 includes a motor and an actuator. The sleeper drive device 32 moves the top plate 33 on which the subject P is placed along the support frame 34 in the longitudinal direction (Z-axis direction) of the top plate 33. The top plate 33 is a plate-shaped member on which the subject P is placed.

The sleeper drive device 32 may move not only the top plate 33 but also the support frame 34 in the longitudinal direction of the top plate 33. Further, contrary to the above, the gantry device 10 may be movable in the Z-axis direction, and the rotation frame 17 may be controlled to come around the subject P by the movement of the gantry device 10. Further, both the gantry device 10 and the top plate 33 may be movable. Further, the X-ray CT device 1 may be a device in which the subject P is scanned in a standing position or a sitting position. In this case, the X-ray CT device 1 has a subject support mechanism instead of the sleeper device 30, and the gantry device 10 rotates the rotating frame 17 about an axial direction perpendicular to the floor surface.

The console device 40 has, for example, a memory 41, a display 42, an input interface 43, a network connection circuit 44, and a processing circuit 50. In the first embodiment, the console device 40 will be described as a separate body from the gantry device 10, but the gantry device 10 may include a part or all of each component of the console device 40.

The memory 41 is realized by, for example, a RAM (Random Access Memory), a semiconductor memory element such as a flash memory, a hard disk, an optical disk, or the like. The memory 41 stores, for example, detection data, projection data, a reconstructed image (CT image), and the like. These data may be stored in an external memory with which the X-ray CT apparatus 1 can communicate, instead of the memory 41 (or in addition to the memory 41). The external memory is controlled by the cloud server, for example, when the cloud server that manages the external memory receives a read / write request. The external memory is realized by, for example, a system called PACS (Picture Archiving and Communication Systems). PACS is a system that systematically stores images and the like taken by various diagnostic imaging devices.

FIG. 2 is a diagram showing an example of data stored in the memory 41. As shown in FIG. 2, in the memory 41, for example, the shooting condition 41-1, the detection data 41-2 output by the DAS 16, the projection data 41-3 generated by the processing circuit 50, and the reconstructed image 41- 4. Information such as the generated image 41-5 and the trained model 41-6 is stored. The generated image 41-5 and the trained model 41-6 will be described later.

The reconstructed image 41-4 includes, for example, a first contrast image 41-4a (first image data), a second contrast image 41-4b (second image data), and a non-contrast image 41-4c. Including. The first contrast image 41-4a is an image obtained by irradiating a subject to which a contrast medium has been administered with high-energy X-rays in a dual energy scan. The second contrast image 41-4b is an image obtained by irradiating a subject to which a contrast medium has been administered with low-energy X-rays in a dual energy scan. The non-contrast image 41-4c is an image obtained by irradiating a subject to which the contrast medium has not been administered or the contrast medium has not reached the imaged region with X-rays.

FIG. 3 is a diagram showing an example of the reconstructed image 41-4 stored in the memory 41. As shown in the figure, in the memory 41, the first contrast image 41-4a, the second contrast image 41-4b, and the non-contrast image 41-4c obtained by photographing the same subject are stored in association with each other. Has been done. For example, with respect to "subject A", the first contrast image 41-4a1, the second contrast image 41-4b1, and the non-contrast image 41-4c1 are stored in association with each other.

The display 42 displays various information. For example, the display 42 displays an image generated by the processing circuit 50, a GUI (Graphical User Interface) image that accepts various operations by the operator, and the like. The display 42 is, for example, a liquid crystal display, a CRT (Cathode Ray Tube), an organic EL (Electroluminescence) display, or the like. The display 42 may be provided on the gantry device 10. The display 42 may be a desktop type or a display device (for example, a tablet terminal) capable of wirelessly communicating with the main body of the console device 40.

The input interface 43 receives various input operations by the operator and outputs an electric signal indicating the contents of the received input operations to the processing circuit 50. For example, the input interface 43 is an input operation such as a collection condition when collecting detection data or projection data, a reconstruction condition when reconstructing a CT image, and an image processing condition when generating a post-processed image from a CT image. Accept. For example, the input interface 43 is realized by a mouse, a keyboard, a touch panel, a trackball, a switch, a button, a joystick, a camera, an infrared sensor, a microphone, and the like. The input interface 43 may be provided on the gantry device 10. Further, the input interface 43 may be realized by a display device (for example, a tablet terminal) capable of wireless communication with the main body of the console device 40.

The network connection circuit 44 includes, for example, a network card having a printed circuit board, a wireless communication module, and the like. The network connection circuit 44 implements an information communication protocol according to the form of the network to be connected. The network includes, for example, a LAN (Local Area Network), a WAN (Wide Area Network), the Internet, a cellular network, a dedicated line, and the like.

The processing circuit 50 controls the overall operation of the X-ray CT apparatus 1. The processing circuit 50 executes, for example, a system control function 51, a preprocessing function 52, a reconstruction processing function 53, an image processing function 54, a scan control function 55, a display control function 56, a generation function 57, a learning function 58, and the like. .. The processing circuit 50 realizes these functions by, for example, the hardware processor executing a program stored in the memory 41.

The hardware processor is, for example, a CPU, a GPU (Graphics Processing Unit), an application specific integrated circuit (ASIC), a programmable logic device (for example, a simple programmable logic device (SPLD)) or It means a circuit (circuitry) such as a complex programmable logic device (CPLD) and a field programmable gate array (FPGA). Instead of storing the program in the memory 41, the program may be configured to be directly embedded in the circuit of the hardware processor. In this case, the hardware processor realizes the function by reading and executing the program embedded in the circuit. The hardware processor is not limited to a single circuit, and may be configured as one hardware processor by combining a plurality of independent circuits to realize each function. Further, a plurality of components may be integrated into one hardware processor to realize each function.

Each component of the console device 40 or the processing circuit 50 may be distributed and implemented by a plurality of hardware. The processing circuit 50 may be realized not by the configuration of the console device 40 but by a processing device capable of communicating with the console device 40. The processing device is, for example, a workstation connected to one X-ray CT device, or a device connected to a plurality of X-ray CT devices and collectively executing processing equivalent to the processing circuit 50 described below (for example,). , Cloud server). That is, it is also possible to realize the configuration of the present embodiment as an X-ray CT system (medical diagnostic system) in which an X-ray CT apparatus and another processing apparatus are connected via a network.

The system control function 51 controls various functions of the processing circuit 50, for example, based on the input operation received by the input interface 43.

The preprocessing function 52 performs preprocessing such as logarithmic conversion processing, offset correction processing, sensitivity correction processing between channels, and beam hardening correction on the detection data 41-2 output by DAS16, and projects data 41-3. Is generated, and the generated projection data 41-3 is stored in the memory 41.

The reconstruction processing function 53 performs reconstruction processing on the projection data 41-3 generated by the preprocessing function 52 by a filter correction back projection method, a successive approximation reconstruction method, or the like to obtain the reconstruction image 41-4. The generated reconstructed image 41-4 is stored in the memory 41.

The image processing function 54 converts the reconstructed image 41-4 into a three-dimensional image or cross-sectional image data of an arbitrary cross section by a known method based on the input operation received by the input interface 43. The conversion to a three-dimensional image may be performed by the preprocessing function 52.

The scan control function 55 controls the collection process of the detection data in the gantry device 10 by instructing the X-ray high voltage device 14, the DAS 16, the control device 18, and the sleeper drive device 32. The scan control function 55 controls the operation of each part when capturing the alignment image, the main captured image, and the image used for diagnosis.

The display control function 56 controls the display mode of the display 42. For example, the display control function 56 controls the display 42 to display a reconstructed image generated by the processing circuit 50, a GUI image that accepts various operations by the operator, and the like.

The generation function 57 inputs the first contrast image 41-4a and the second contrast image 41-4b generated by the reconstruction processing function 53 to the trained model 41-6, whereby the reconstruction image 41 In -4, an image (generated image 41-5) in which the influence of the specific substance is reduced is generated. For example, the specific substance is a contrast medium or a substance having calcium in its composition.

FIG. 4 is a diagram showing an example of the functional configuration of the generation function 57. As shown in the figure, the generation function 57 includes, for example, an acquisition function 57-1 (acquisition unit) and a data generation function 57-2 (data generation unit). The acquisition function 57-1 acquires the first contrast image 41-4a and the second contrast image 41-4b generated by the reconstruction processing function 53. The data generation function 57-2 reads the trained model 41-6 from the memory 41, and with respect to the read trained model 41-6, the first contrast image 41-4a and the first contrast image 41-4a acquired by the acquisition function 57-1. 2 By inputting the contrast image 41-4b, the generated image 41-5 is generated. The data generation function 57-2 stores the generated generated image 41-5 in the memory 41.

The learning function 58 includes a plurality of data sets corresponding to a plurality of X-ray energies obtained by performing an X-ray scan on an object (for example, a living body, a phantom, etc.) containing a specific substance, and the above-mentioned identification. By learning the relationship with a single data set obtained by performing an X-ray scan on a substance-free object, when the above multiple data sets are input, the above single data set Generate a trained model 41-6 trained to output one dataset.

FIG. 5 is a diagram showing an example of the functional configuration of the learning function 58. As shown in the figure, the learning function 58 includes, for example, a first acquisition function 58-1, a second acquisition function 58-2, and a model generation function 58-3. The first acquisition function 58-1 is a plurality of reconstructions generated by the reconstruction processing function 53 based on a plurality of data sets obtained by irradiating a subject containing a specific substance with a plurality of X-ray energies. The configuration image 41-4 is acquired. The first acquisition function 58-1 acquires, for example, the first contrast image 41-4a and the second contrast image 41-4b.

The second acquisition function 58-2 displays the reconstruction image 41-4 generated by the reconstruction processing function 53 based on the data obtained by irradiating the subject containing no specific substance with X-ray energy. get. The second acquisition function 58-2 acquires, for example, a non-contrast image 41-4c.

The model generation function 58-3 is obtained by performing an X-ray scan on a subject containing a specific substance by learning by inputting a plurality of data sets and outputting a single data set. By inputting multiple data sets that are compatible with X-ray energy and separate from multiple data sets, a single data set that is different from the single data set that is less affected by specific substances can be created. Generate a trained model 41-6 to generate.

For example, the model generation function 58-3 performs learning by inputting the first contrast image 41-4a and the second contrast image 41-4b and outputting the non-contrast image 41-4c. For example, in the model generation function 58-3, the difference between the data output when the first contrast image 41-4a and the second contrast image 41-4b are input to the model and the data of the non-contrast image 41-4c is Various parameters in the model are learned by using gradient methods such as SGD (Stochastic Gradient Descent), Momentum SGD, AdaGrad, RMSrop, AdaDelta, and Adam (Adaptive moment estimation) so as to be small. The model generation function 58-3 may use a model generated by any machine learning such as a neural network (for example, CNN: Convolution Neural Network), logistic regression analysis, or a technology based on a support vector machine. ..

With the above configuration, the X-ray CT apparatus 1 scans the subject P in a manner such as a helical scan, a conventional scan, and a step-and-shoot. The helical scan is a mode in which the rotating frame 17 is rotated while the top plate 33 is moved to spirally scan the subject P. The conventional scan is a mode in which the rotating frame 17 is rotated while the top plate 33 is stationary to scan the subject P in a circular orbit. Perform a conventional scan. The step-and-shoot is a mode in which the position of the top plate 33 is moved at regular intervals to perform a conventional scan in a plurality of scan areas.

[Processing flow (learning stage)]
Hereinafter, the processing flow of the processing circuit 50 in the first embodiment will be described. The processing of the processing circuit 50 includes a learning process for generating the trained model 41-6 and a generation process for generating the generated image 41-5 using the trained model 41-6. In the following, first, the learning process by the processing circuit 50 will be described. FIG. 6 is a flowchart showing a series of flow of learning processing of the processing circuit 50. FIG. 7 is a diagram showing the relationship between model input and output in the learning process of the processing circuit 50. The processing of the flowchart shown in FIG. 6 is started, for example, when the operator of the X-ray CT apparatus 1 operates the input interface 43 to instruct the start of the learning process. The processing of the flowchart shown in FIG. 6 uses a large number of image sets (multiple sets of a set of a first contrast image 41-4a, a second contrast image 41-4b, and a non-contrast image 41-4c associated with each other). It is repeated. In the following, it is assumed that the reconstructed image 41-4, which is the learning data, has already been collected and stored in the memory 41.

First, the first acquisition function 58-1 of the learning function 58 uses the reconstructed images 41-4 stored in the memory 41 as learning data, and the first contrast images 41-4a and the second contrast images 41-4a associated with each other are used. Acquire a set (a plurality of data sets) with the contrast image 41-4b (step S100, first acquisition step). The pair of the first contrast image 41-4a and the second contrast image 41-4b is an image obtained by irradiating the same subject with X-rays. In the example shown in FIG. 3, the first acquisition function 58-1 is a set of "first contrast image 41-4a1" and "second contrast image 41-4b1", "first contrast image 41-4a2" and ". A pair with the "second contrast image 41-4b2", a pair with the "first contrast image 41-4a3" and the "second contrast image 41-4b3", and the like are acquired. That is, the first acquisition function 58-1 acquires a plurality of data sets corresponding to a plurality of X-ray energies obtained by performing an X-ray scan on an object containing a specific substance.

Next, the second acquisition function 58-2 of the learning function 58 uses the first contrast image 41-4a acquired by the first acquisition function 58-1 from the reconstructed images 41-4 stored in the memory 41. And the non-contrast image 41-4c (single data set) associated with the pair of the second contrast image 41-4b (step S102, second acquisition step). In the example shown in FIG. 3, the second acquisition function 58-2 acquires "non-contrast image 41-4c1", "non-contrast image 41-4c2", "non-contrast image 41-4c3" and the like. That is, the second acquisition function 58-2 acquires a single data set obtained by performing an X-ray scan on an object that does not contain a specific substance.

Next, the model generation function 58-3 of the learning function 58 inputs the first contrast image 41-4a and the second contrast image 41-4b acquired by the first acquisition function 58-1 into the model M1, and the model M1 thereof. Obtain the processing result (step S104).

Next, the model generation function 58-3 calculates the difference between the processing result data and the non-contrast image 41-4c data (step S106). In the example shown in FIG. 3, the processing result data obtained by inputting the pair of the “first contrast image 41-4a1” and the “second contrast image 41-4b1” into the model M1 and the “non-contrast image”. Calculate the difference from the data of "41-4c1".

Next, the model generation function 58-3 updates the internal parameters of the model M1 based on the calculated difference (step S108). For example, the model generation function 58-3 updates the internal parameters of the model M1 so that the calculated difference becomes small. The model generation function 58-3 is a set of "first contrast image 41-4a1", "second contrast image 41-4b1", and "non-contrast image 41-4c1", "first contrast image 41-4a2", A set of "second contrast image 41-4b2" and "non-contrast image 41-4c2", as well as "first contrast image 41-4a3", "second contrast image 41-4b3", and "non-contrast image 41-". Using each set of "4c3", the update processing of the internal parameters of the model M1 is repeatedly performed (loop processing). The model M1 whose internal parameters have been updated in this way becomes the trained model 41-6. The learning function 58 stores the learned model 41-6 in the memory 41 (step S110). As described above, the learning step by the model generation function 58-3 is completed, and the processing of this flowchart is completed.

The non-contrast image 41-4c used as the correct answer data includes the first contrast image 41-4a and the second contrast image 41-4b in addition to (or instead of) the image actually taken without contrast. An image obtained by modifying the VNC image based on the image by a person may be included. That is, in addition to (or instead of) step S102 above, for example, the generation function 57 generates a VNC image based on the first contrast image 41-4a and the second contrast image 41-4b (plural datasets). (Generation step), and the generated VNC image may be modified.

[Processing flow (generation processing)]
Next, the generation process of the generated image 41-5 by the processing circuit 50 will be described. FIG. 8 is a flowchart showing a series of flow of generation processing by the processing circuit 50. The processing of this flowchart is started, for example, when the operator of the X-ray CT apparatus 1 operates the input interface 43 to instruct to start the generation processing of the generated images 41-5 after acquiring the contrast image of the subject. Will be done.

First, the acquisition function 57-1 of the generation function 57 includes the first contrast image 41-4a and the second contrast image 41-4b to be processed from the reconstructed images 41-4 stored in the memory 41. Acquire a pair (step S200).

Next, the data generation function 57-2 of the generation function 57 reads the trained model 41-6 from the memory 41, and the first contrast image 41-4a and the second contrast image 41- acquired by the acquisition function 57-1. 4b is input to the trained model 41-6, and the generated image 41-5, which is the output of the trained model 41-6, is generated (step S202).

Next, the data generation function 57-2 stores the generated generated image 41-5 in the memory 41 (step S204). This completes the processing of this flowchart. For example, the operator of the X-ray CT apparatus 1 can operate the input interface 43 to display the generated image 41-5 generated as described above on the display 42 for confirmation.

According to the X-ray CT apparatus 1 of the first embodiment described above, it is possible to obtain a high-quality image in which the influence of a specific substance is reduced. For example, by inputting a contrast image of a subject into the trained model 41-6, a high-quality non-contrast image in which the influence of the contrast agent is reduced can be obtained from the contrast image. In this non-contrast image, no unnatural portion remains at the edge of the portion containing the specific substance in the original contrast image, and the visibility can be improved. Further, since it is not necessary to take a non-contrast image of the subject, it is possible to reduce the chance of irradiating the subject with X-rays and reduce the time and labor required for CT imaging. In addition, since the non-contrast image is generated from the contrast image, the position shift of the imaged portion of the subject occurs, which has occurred when the contrast image is photographed and the non-contrast image is photographed separately as in the conventional case. do not do. Therefore, it becomes easy to compare the contrast-enhanced image and the non-contrast-enhanced image.

In the above embodiment, the case where the model generation function 58-3 learns the entire contrast-enhanced image and non-contrast-enhanced image has been described as an example, but the present invention is not limited to this. For example, the model generation function 58-3 may locally learn the image (2D, 3D) to generate a trained model. Further, the model generation function 58-3 may train the image for each segment (2D, 3D) to generate a trained model. Further, the model generation function 58-3 may learn the image for each organ and each blood vessel size to generate a trained model. In addition, the model generation function 58-3 may learn what is excluded, such as bone (a part that does not change due to contrast enhancement).

Further, the model generation function 58-3 may perform learning by inputting a VNC image and outputting a non-contrast image 41-4c. Further, the model generation function 58-3 may learn a low-quality VNC image including an unnatural part as incorrect answer data. The data generation function 57-2 may mix the generated generated image 41-5 and the VNC image.

(Second embodiment)
Hereinafter, the second embodiment will be described. In the first embodiment described above, an example has been described in which the generation function 57 generates the generated image 41-5 by using the reconstructed image 41-4 generated by the reconstructing processing function 53. On the other hand, in the second embodiment, the generation function 57 generates the generated image 41-5 using the detection data 41-2 (raw data) output by the DAS 16. Therefore, for the configuration and the like, the drawings and related descriptions described in the first embodiment will be referred to, and detailed description will be omitted.

FIG. 9 is a diagram showing an example of data stored in the memory 41. As shown in the figure, the detection data 41-2 includes, for example, the first detection data 41-2a (first data), the second detection data 41-2b (second data), and the third detection data 41-. Includes 2c. The first detection data 41-2a is raw data obtained by irradiating a subject to which a contrast medium has been administered with high-energy X-rays in a dual energy scan. The second detection data 41-2b is raw data obtained by irradiating a subject to which a contrast medium has been administered with low-energy X-rays in a dual energy scan. The third detection data 41-2c is raw data obtained by irradiating a subject to which the contrast medium has not been administered or the contrast medium has not reached the imaged region with X-rays. In the memory 41, the first detection data 41-2a, the second detection data 41-2b, and the third detection data 41-2c obtained by photographing the same subject are stored in association with each other.

FIG. 10 is a diagram showing an example of detection data 41-2 stored in the memory 41. As shown in the figure, in the memory 41, the first detection data 41-2a, the second detection data 41-2b, and the third detection data 41-2c obtained by photographing the same subject are related to each other. It is remembered. For example, regarding "subject A", the first detection data 41-2a1, the second detection data 41-2b1, and the third detection data 41-2c1 are stored in association with each other.

[Processing flow (learning stage)]
Hereinafter, the processing flow of the processing circuit 50 in the second embodiment will be described. The processing of the processing circuit 50 includes a learning process for generating the trained model 41-6 and a generation process for generating the generated image 41-5 using the trained model 41-6. In the following, first, the learning process by the processing circuit 50 will be described. FIG. 11 is a flowchart showing a series of flow of learning processing of the processing circuit 50. FIG. 12 is a diagram showing the relationship between model input and output in the learning process of the processing circuit 50. The processing of the flowchart shown in FIG. 11 is started, for example, when the operator of the X-ray CT apparatus 1 operates the input interface 43 to instruct the start of the learning process. The processing of the flowchart shown in FIG. 11 uses a large number of detection data sets (multiple sets of a set of first detection data 41-2a, second detection data 41-2b, and non-contrast image 41-4c associated with each other). Is repeated. In the following, it is assumed that the detection data 41-2, which is the learning data, has already been collected and stored in the memory 41.

First, the first acquisition function 58-1 of the learning function 58 uses the detection data 41-2 stored in the memory 41 as learning data, that is, the first detection data 41-2a and the second detection that are related to each other. Acquire the pair with the data 41-2b (step S300, first acquisition step). The set of the first detection data 41-2a and the second detection data 41-2b is an image obtained by irradiating the same subject with X-rays. In the example shown in FIG. 10, the first acquisition function 58-1 is a set of "first detection data 41-2a1" and "second detection data 41-2b1", "first detection data 41-2a2" and ". A pair of "second detection data 41-2b2", a pair of "first detection data 41-2a3" and "second detection data 41-2b3", and the like are acquired.

Next, the second acquisition function 58-2 of the learning function 58 uses the first detection data 41-2a acquired by the first acquisition function 58-1 from the reconstructed images 41-4 stored in the memory 41. The non-contrast image 41-4c associated with the pair of the second detection data 41-2b and the second detection data 41-2b is acquired (step S302, second acquisition step). In the examples shown in FIGS. 3 and 10, the second acquisition function 58-2 describes the “first detection data 41-2a1” and “second detection” acquired by the first acquisition function 58-1 with respect to the “subject A”. The "non-contrast image 41-4c1" associated with the "data 41-2b1" is acquired. Further, the second acquisition function 58-2 associates the "subject B" with the "first detection data 41-2a2" and the "second detection data 41-2b2" acquired by the first acquisition function 58-1. The "non-contrast image 41-4c2" to be obtained is acquired. Further, the second acquisition function 58-2 associates the "subject C" with the "first detection data 41-2a3" and the "second detection data 41-2b3" acquired by the first acquisition function 58-1. The "non-contrast image 41-4c3" to be obtained is acquired.

Next, the model generation function 58-3 of the learning function 58 inputs the first detection data 41-2a and the second detection data 41-2b acquired by the first acquisition function 58-1 into the model M2, and inputs the first detection data 41-2a and the second detection data 41-2b into the model M2. Obtain the processing result (step S304).

Next, the model generation function 58-3 calculates the difference between the processing result data and the non-contrast image 41-4c data (step S306).

Next, the model generation function 58-3 updates the internal parameters of the model M2 based on the calculated difference (step S308). Here, the model generation function 58-3 will perform learning including the reconstruction process of the detection data 41-2. For example, the model generation function 58-3 updates the internal parameters of the model M2 so that the calculated difference becomes small. The model generation function 58-3 is a set of "first detection data 41-2a1", "second detection data 41-2b1", and "non-contrast image 41-4c1", "first detection data 41-2a2", A set of "second detection data 41-2b2" and "non-contrast image 44-1c2", and "first detection data 41-2a3", "second detection data 41-2b3", and "non-contrast image 41-". Using each set of "4c3", the update process of the internal parameters of the model M1 is repeatedly performed (loop process). The model M2 whose internal parameters have been updated in this way becomes the trained model 41-6. The learning function 58 stores the learned model 41-6 in the memory 41 (step S310). As a result, the learning step by the model generation function 58-3 is completed, and the processing of this flowchart is completed.

The non-contrast image 41-4c used as the correct answer data includes the first contrast image 41-4a and the second contrast image 41-4b in addition to (or instead of) the image actually taken without contrast. An image obtained by modifying the VNC image based on the image by a person may be included.

[Processing flow (generation processing)]
Next, the generation process of the generated image 41-5 by the processing circuit 50 will be described. FIG. 13 is a flowchart showing a series of flow of generation processing by the processing circuit 50. The processing of this flowchart is started, for example, when the operator of the X-ray CT apparatus 1 operates the input interface 43 to instruct to start the generation processing of the generated images 41-5 after acquiring the contrast image of the subject. Will be done.

First, the acquisition function 57-1 of the generation function 57 sets the first detection data 41-2a and the second detection data 41-2b to be processed from the detection data 41-2 stored in the memory 41. (Step S400).

Next, the data generation function 57-2 of the generation function 57 reads the trained model 41-6 from the memory 41, and the first detection data 41-2a and the second detection data 41- acquired by the acquisition function 57-1. 2b is input to the trained model 41-6, and the generated image 41-5, which is the output of the trained model 41-6, is generated (step S402).

Next, the data generation function 57-2 stores the generated generated image 41-5 in the memory 41 (step S404). This completes the processing of this flowchart. For example, the operator of the X-ray CT apparatus 1 can operate the input interface 43 to display the generated image 41-5 generated as described above on the display 42 for confirmation.

According to the X-ray CT apparatus 1 of the second embodiment described above, it is possible to obtain a high-quality image in which the influence of a specific substance is reduced. For example, by inputting the detection data of the subject to which the contrast medium is administered into the trained model 41-6, it is possible to obtain a high-quality non-contrast image in which the influence of the contrast medium is reduced. In this non-contrast image, no unnatural portion remains at the edge of the portion containing the specific substance in the original contrast image, and the visibility can be improved. Further, since it is not necessary to take a non-contrast image of the subject, it is possible to reduce the chance of irradiating the subject with X-rays and reduce the time and labor required for CT imaging. In addition, since the non-contrast image is generated from the contrast image, the position shift of the imaged portion of the subject occurs, which has occurred when the contrast image is photographed and the non-contrast image is photographed separately as in the conventional case. do not do. Therefore, it becomes easy to compare the contrast-enhanced image and the non-contrast-enhanced image.

In the dual energy scan, if a method is adopted in which the subject is irradiated with low-energy X-rays and high-energy X-rays at almost the same time while switching the tube voltage of the X-ray tube at high speed, the detection data 41-2 is a mixture of high-energy X-ray-based data and low-energy X-ray-based data. In this case, the model generation function 58-3 may perform learning by inputting the detection data in which the two types of data are mixed and using the non-contrast image 41-4c as the output. FIG. 14 is a diagram showing another example of the relationship between the model input and the output in the learning process of the processing circuit 50. As shown in the figure, learning may be performed by inputting detection data 41-2m in which two types of data are mixed and outputting non-contrast image 41-4c. The model generation function 58-3 separates the detection data 41-2m, which is a mixture of two types of data, into high-energy X-ray-based data and low-energy X-ray-based data, and re-images based on each data. You will learn including the constituent processes.

In the X-ray CT apparatus 1 of the first and second embodiments described above, the model generation function 58-3 uses the detection data (raw data) or the reconstructed image (raw data) obtained by irradiating the subject with X-rays. An example of using (image data) as a model input has been described, but the present invention is not limited to this. For example, the model generation function 58-3 irradiates the object with data obtained by irradiating the object with X-rays having the first energy and X-rays having a second energy lower than the first energy. The raw data or image data of the reference substance obtained by performing the Material Decomposition analysis (material discrimination) with respect to the data obtained by the above may be used as the input of the model.

(Third Embodiment)
Hereinafter, the third embodiment will be described. In the first and second embodiments described above, an example has been described in which the generation function 57 generates a generated image 41-5 in which the influence of the component of the contrast medium as a specific substance is reduced. On the other hand, in the third embodiment, the production function 57 produces a generated image 41-5 in which the influence of the calcium component as a specific substance (such as a calcified part in the human body) is reduced. explain. Therefore, for the configuration and the like, the drawings and related descriptions described in the first embodiment will be referred to, and detailed description will be omitted.

FIG. 15 is a diagram showing an example of data stored in the memory 41. As shown, the reconstructed image 41-4 includes, for example, a first Ca-containing image 41-4d, a second Ca-containing image 41-4e, and a Ca-free image 41-4f. The first Ca-containing image 41-4d is an image obtained by irradiating a subject having calcium as a composition to which a contrast medium has been administered with high-energy X-rays in a dual energy scan. The second Ca-containing image 41-4e is an image obtained by irradiating a subject having calcium as a composition to which a contrast medium has been administered with low-energy X-rays in a dual energy scan. The Ca-free image 41-4f is an image that does not contain a calcium component. When using an image obtained by photographing a patient as a subject, the Ca-free image 41-4f is obtained from, for example, the first Ca-containing image 41-4d and / or the second Ca-containing image 41-4e obtained by photographing. It may be produced by human modification to remove the calcium component. Alternatively, the Ca-free image 41-4f is manually corrected after the calcium component is computationally removed from the first Ca-containing image 41-4d and / or the second Ca-containing image 41-4e obtained by photographing. It may be generated by being performed. When a phantom is used, the Ca-free image 41-4f may be obtained by taking a picture in a state where the phantom does not contain Ca. For example, a Ca-containing image and a Ca-free image can be obtained by performing two types of shooting, one is when Ca is put in a specific space in the phantom and the other is when water is put in. When animal meat or the like is used, a Ca-containing image and a Ca-free image can be obtained by taking pictures before and after placing Ca. In the memory 41, the first Ca-containing image 41-4d, the second Ca-containing image 41-4e, and the Ca-free image 41-4f obtained by photographing the same subject are stored in association with each other.

FIG. 16 is a diagram showing an example of the reconstructed image 41-4 stored in the memory 41. As shown in the figure, in the memory 41, the first Ca-containing image 41-4d, the second Ca-containing image 41-4e, and the Ca-free image 41-4f obtained by photographing the same subject are associated with each other. It is remembered. For example, with respect to "subject A", the first Ca-containing image 41-4d1, the second Ca-containing image 41-4e1, and the Ca-free image 41-4f1 are stored in association with each other.

[Processing flow (learning stage)]
Hereinafter, the processing flow of the processing circuit 50 in the third embodiment will be described. The processing of the processing circuit 50 includes a learning process for generating the trained model 41-6 and a generation process for generating the generated image 41-5 using the trained model 41-6. In the following, first, the learning process by the processing circuit 50 will be described. FIG. 17 is a flowchart showing a series of flow of learning processing of the processing circuit 50. FIG. 18 is a diagram showing the relationship between model input and output in the learning process of the processing circuit 50. The processing of the flowchart shown in FIG. 17 is started, for example, when the operator of the X-ray CT apparatus 1 operates the input interface 43 to instruct the start of the learning process. The processing of the flowchart shown in FIG. 17 uses a large number of image sets (a plurality of sets of a set of a first Ca-containing image 41-4d, a second Ca-containing image 41-4e, and a Ca-free image 41-4f associated with each other). Is repeated. In the following, it is assumed that the reconstructed image 41-4, which is the learning data, has already been collected and stored in the memory 41.

First, the first acquisition function 58-1 of the learning function 58 uses the first Ca-containing images 41-4d and the second Ca, which are associated with each other, as learning data from the reconstructed images 41-4 stored in the memory 41. A pair with the contained image 41-4e is acquired (step S500). The pair of the first Ca-containing image 41-4d and the second Ca-containing image 41-4e is an image obtained by irradiating the same subject with X-rays. In the example shown in FIG. 16, the first acquisition function 58-1 is a set of "first Ca-containing image 41-4d1" and "second Ca-containing image 41-4e1", "first Ca-containing image 41-4d2" and "1st Ca-containing image 41-4d2". A pair with the "second Ca-containing image 41-4e2", a pair with the "first Ca-containing image 41-4d3" and the "second Ca-containing image 41-4e3", and the like are acquired.

Next, the second acquisition function 58-2 of the learning function 58 is the first Ca-containing image 41-4d acquired by the first acquisition function 58-1 from the reconstructed images 41-4 stored in the memory 41. And the Ca-free image 41-4f associated with the pair of the second Ca-containing image 41-4e is acquired (step S502). In the example shown in FIG. 16, the second acquisition function 58-2 acquires "Ca-free image 41-4f1", "Ca-free image 41-4f2", "Ca-free image 41-4f3" and the like.

Next, the model generation function 58-3 of the learning function 58 inputs the first Ca-containing image 41-4d and the second Ca-containing image 41-4e acquired by the first acquisition function 58-1 into the model M4, and inputs the first Ca-containing image 41-4d and the second Ca-containing image 41-4e to the model M4. The processing result is obtained (step S504).

Next, the model generation function 58-3 calculates the difference between the processing result data and the data of the Ca-free image 41-4f (step S506). In the example shown in FIG. 16, the processing result data obtained by inputting the set of the "first Ca-containing image 41-4d1" and the "second Ca-containing image 41-4e1" into the model M4 and the "Ca-free image" Calculate the difference from the data of "41-4f1".

Next, the model generation function 58-3 updates the internal parameters of the model M4 based on the calculated difference (step S508). For example, the model generation function 58-3 updates the internal parameters of the model M4 so that the calculated difference becomes small. The model generation function 58-3 is a set of "first Ca-containing image 41-4d1", "second Ca-containing image 41-4e1", and "Ca-free image 41-4f1", "first Ca-containing image 41-4d2". , "Second Ca-containing image 41-4e2", and "Ca-free image 41-4f2", and "First Ca-containing image 41-4d3", "Second Ca-containing image 41-4e3", and "Ca-free image 41-4e3". Using each set of "Image 41-4f3", the update process of the internal parameters of the model M4 is repeated (loop process). The model M4 whose internal parameters have been updated in this way becomes the trained model 41-6. The learning function 58 stores the learned model 41-6 in the memory 41 (step S510). This completes the processing of this flowchart.

[Processing flow (generation processing)]
Next, the generation process of the generated image 41-5 by the processing circuit 50 will be described. FIG. 19 is a flowchart showing a series of flow of generation processing by the processing circuit 50. The processing of this flowchart is started, for example, when the operator of the X-ray CT apparatus 1 operates the input interface 43 to instruct to start the generation processing of the generated images 41-5 after acquiring the contrast image of the subject. Will be done.

First, the acquisition function 57-1 of the generation function 57 includes the first Ca-containing image 41-4d and the second Ca-containing image 41-4e to be processed from the reconstructed images 41-4 stored in the memory 41. Acquire a pair (step S600).

Next, the data generation function 57-2 of the generation function 57 reads the trained model 41-6 from the memory 41, and the first Ca-containing image 41-4d and the second Ca-containing image 41- acquired by the acquisition function 57-1. 4e is input to the trained model 41-6, and the generated image 41-5, which is the output of the trained model 41-6, is generated (step S602).

Next, the data generation function 57-2 stores the generated generated image 41-5 in the memory 41 (step S604). This completes the processing of this flowchart. For example, the operator of the X-ray CT apparatus 1 can operate the input interface 43 to display the generated image 41-5 generated as described above on the display 42 for confirmation.

According to the X-ray CT apparatus 1 of the third embodiment described above, it is possible to obtain a high-quality image in which the influence of a specific substance is reduced. For example, by inputting the detection data of the subject into the trained model 41-6, it is possible to obtain a high-quality image in which the influence of calcium is reduced. In the image in which the influence of the calcium component is reduced, no unnatural portion remains on the edge of the portion containing the calcium component in the original image, and the visibility can be improved.

In the third embodiment described above, an example in which the generation function 57 generates the generated image 41-5 by using the reconstruction image 41-4 generated by the reconstruction processing function 53 has been described. Similar to the second embodiment, the generation function 57 may generate the generated image 41-5 using the detection data 41-2 (raw data) output by the DAS 16. Further, the learning may be performed by inputting the detection data in which the two types of data are mixed and outputting the Ca exclusion image.

The embodiment described above can be expressed as follows.
The memory to store the program and
With a processor,
The processor executes the program.
A plurality of data sets corresponding to a plurality of X-ray energies obtained by performing an X-ray scan on an object containing a specific substance are input, and X is applied to the object not containing the specific substance. The plurality of X-ray energies obtained by performing an X-ray scan on a subject containing the specific substance by learning using a single data set obtained by performing a line scan as an output. By inputting a plurality of data sets different from the plurality of data sets, a single data set different from the single data set is generated in which the influence of the specific substance is reduced. By inputting the other plurality of data sets to the trained model for generating the other single data set.
Medical processing equipment.

According to at least one embodiment described above, the trained model generation method corresponds to a plurality of X-ray energies obtained by performing an X-ray scan on an object containing a specific substance. A first acquisition step to acquire the data set of, and a second acquisition step to acquire a single data set obtained by performing an X-ray scan on an object containing no specific substance. Corresponds to multiple X-ray energies obtained by performing an X-ray scan on a subject containing a specific substance by learning with the data set of Generate a trained model to generate a single dataset separate from the single dataset with reduced effects of specific substances by entering multiple datasets separate from the dataset in By including the learning steps to be performed, it is possible to obtain a high-quality image in which the influence of a specific substance is reduced.

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 embodiments, and various mitigations, replacements, and modifications can be made without departing from the gist of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, as well as in the scope of the invention described in the claims and the equivalent scope thereof.

1 ... X-ray CT device, 10 ... gantry device, 11 ... X-ray tube, 12 ... wedge, 13 ... collimeter, 14 ... X-ray high voltage device, 15 ... X-ray detector, 16 ... data acquisition system, 17 ... rotation Frame, 18 ... Control device, 30 ... Sleep device, 31 ... Base, 32 ... Sleep drive device, 33 ... Top plate, 34 ... Support frame, 40 ... Console device, 50 ... Processing circuit, 51 ... System control function, 52 ... preprocessing function, 53 ... reconstruction processing function, 54 ... image processing function, 55 ... scan control function, 56 ... display control function, 57 ... generation function, 57-1 ... acquisition function, 57-2 ... data generation function, 58 ... Learning function, 58-1 ... 1st acquisition function, 58-2 ... 2nd acquisition function, 58-3 ... Model generation function

Claims (10)

The first acquisition step of acquiring a plurality of data sets corresponding to a plurality of X-ray energies obtained by performing an X-ray scan on an object containing a specific substance, and
A second acquisition step of acquiring a single data set obtained by performing an X-ray scan on the object that does not contain the specific substance.
The plurality of X-ray energies obtained by performing an X-ray scan on a subject containing the specific substance by learning using the plurality of data sets as inputs and the single data set as an output. By inputting a plurality of data sets different from the plurality of data sets, a single data set different from the single data set is generated in which the influence of the specific substance is reduced. And the learning steps to generate a trained model to do
How to generate a trained model, including. An acquisition step of acquiring a plurality of data sets corresponding to a plurality of X-ray energies obtained by performing an X-ray scan on an object containing a specific substance.
A generation step based on the plurality of data sets to generate a single data set with reduced effects of the specific substance.
The plurality of X-ray energies obtained by performing an X-ray scan on a subject containing the specific substance by learning using the plurality of data sets as inputs and the single data set as an output. By inputting a plurality of data sets different from the plurality of data sets, a single data set different from the single data set is generated in which the influence of the specific substance is reduced. And the learning steps to generate a trained model to do
How to generate a trained model, including. The specific substance is a contrast medium or a substance having calcium in its composition.
The method for generating a trained model according to claim 1 or 2. The generation step
To generate a virtual non-contrast image based on the plurality of data sets,
To modify the generated virtual non-contrast image,
including,
The method for generating a trained model according to claim 2. The plurality of data sets include a first image data generated based on data obtained by irradiating the object with X-rays having a first energy, and a second image data having a lower energy than the first energy. Includes a second image data generated based on the data obtained by irradiating the object with X-rays of energy.
The method for generating a trained model according to any one of claims 1 to 4. The plurality of data sets include first data obtained by irradiating the object with X-rays having a first energy and X-rays having a second energy lower than the first energy. Includes a second data obtained by irradiating the
The method for generating a trained model according to any one of claims 1 to 4. The plurality of data sets include first data obtained by irradiating the object with X-rays having a first energy and X-rays having a second energy lower than the first energy. Includes data mixed with the second data obtained by irradiating
The method for generating a trained model according to any one of claims 1 to 4. The plurality of data sets irradiate the object with data obtained by irradiating the object with X-rays having a first energy and X-rays having a second energy lower than the first energy. Including the raw data of the reference substance obtained by performing substance discrimination against the data obtained by
The method for generating a trained model according to any one of claims 1 to 4. The plurality of data sets irradiate the object with data obtained by irradiating the object with X-rays having a first energy and X-rays having a second energy lower than the first energy. Including the image data of the reference substance obtained by performing substance discrimination with respect to the data obtained by the above.
The method for generating a trained model according to any one of claims 1 to 4. The trained model generated by the method for generating a trained model according to any one of claims 1 to 9, and the trained model.
An acquisition unit that acquires a plurality of the other data sets, and
A data generation unit that generates the other single data set by inputting the other plurality of data sets to the trained model.
Medical processing device equipped with.

Images