Medical image processing method, medical image processing device, and X-ray CT device

Abstract

To improve the image quality of a reference substance image.SOLUTION: A medical image processing method according to an embodiment comprises the steps of: acquiring a first monochrome X-ray image corresponding to the first X-ray energy and a second monochrome X-ray image corresponding to the second X-ray energy; acquiring a first corrected monochrome X-ray image by applying the first image processing corresponding to the first X-ray energy to the first monochrome X-ray image; acquiring a second corrected monochrome X-ray image by applying the second image processing corresponding to the second X-ray energy and different from the first image processing to the second monochrome X-ray image; and generating a plurality of corrected reference substance images on the basis of the first corrected monochrome X-ray image and the second corrected monochrome X-ray image.SELECTED DRAWING: Figure 5

Description

[Technical field]

[0001] The embodiments disclosed in this specification relate to a medical image processing method, a medical image processing apparatus, and an X-ray CT apparatus. [Background technology]

[0002] Conventionally, X-ray computed tomography (CT) devices have been widely used in clinical settings. With an X-ray CT device, it is possible to collect projection data by irradiating an object with X-rays, and reconstruct a CT image in which CT value information is assigned to each pixel. In recent years, applied technology has also been used to generate an image (reference material image) based on the abundance rate of a reference material, based on the projection data collected by the X-ray CT device. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2014-144274 A Summary of the Invention [Problem to be solved by the invention]

[0004] One of the problems that the embodiments disclosed in the present specification are intended to solve is to improve the image quality of a reference material image. However, the problems solved by the embodiments disclosed in the present specification are not limited to the above problem. Problems corresponding to the effects of each configuration shown in the embodiments described later can also be considered as other problems solved by the embodiments disclosed in the present specification. [Means for solving the problem]

[0005] A medical image processing method of an embodiment includes acquiring a first monochromatic X-ray image corresponding to a first X-ray energy and a second monochromatic X-ray image corresponding to a second X-ray energy, obtaining a first corrected monochromatic X-ray image by applying a first image processing corresponding to the first X-ray energy to the first monochromatic X-ray image, obtaining a second corrected monochromatic X-ray image by applying a second image processing corresponding to the second X-ray energy and different from the first image processing to the second monochromatic X-ray image, and generating a plurality of corrected reference material images based on the first corrected monochromatic X-ray image and the second corrected monochromatic X-ray image. [Brief description of the drawings]

[0006] [Figure 1] FIG. 1 is a block diagram showing an example of the configuration of a medical image processing system according to the first embodiment. [Diagram 2] FIG. 2 is a block diagram showing an example of the configuration of the X-ray CT apparatus according to the first embodiment. [Diagram 3] FIG. 3 is a diagram showing an example of processing of the medical image processing system according to the first embodiment. [Figure 4] FIG. 4 is a diagram showing a series of processes of the processing circuit according to the first embodiment. [Diagram 5] FIG. 5 is a diagram showing a series of processes of the processing circuit according to the first embodiment. [Figure 6] FIG. 6 is a diagram for explaining an example of image processing according to the first embodiment. [Figure 7] FIG. 7 is a flowchart for explaining a series of processing steps of the medical image processing apparatus according to the first embodiment. [Figure 8] FIG. 8 is a block diagram showing an example of the configuration of an X-ray CT apparatus 10 according to the second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0007] Hereinafter, embodiments of a medical image processing method, a medical image processing apparatus, and an X-ray CT apparatus will be described in detail with reference to the accompanying drawings.

[0008] (First embodiment) In this embodiment, as shown in Fig. 1, a medical image processing system 1 including an X-ray CT device 10 and a medical image processing device 20 will be described as an example. Fig. 1 is a block diagram showing an example of the configuration of the medical image processing system 1 according to the first embodiment. In this embodiment, the description will be given assuming that each process described below is executed based on projection data collected by the X-ray CT device 10 shown in Fig. 1. The X-ray CT device 10 and the medical image processing device 20 are connected to each other via a network NW.

[0009] In addition, the X-ray CT device 10 and the medical image processing device 20 may be installed at any location as long as they can be connected via the network NW. For example, the X-ray CT device 10 and the medical image processing device 20 may be installed in different facilities. That is, the network NW may be configured as a closed local network within the facility, or may be a network via the Internet. In addition, communication between the X-ray CT device 10 and the medical image processing device 20 may be performed via another device such as an image storage device, or may be performed directly without using another device. An example of such an image storage device is a server of a PACS (Picture Archiving and Communication System).

[0010] The medical image processing device 20 executes various processes including generation of a reference material image based on the data set collected by the X-ray CT device 10. For example, the medical image processing device 20 includes a memory 21, a display 22, an input interface 23, and a processing circuit 24, as shown in FIG.

[0011] The memory 21 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory), a flash memory, a hard disk, an optical disk, etc. For example, the memory 21 stores a program for enabling a circuit included in the medical image processing device 20 to realize its function. The memory 21 also stores various data received from the X-ray CT device 10. The memory 21 may be realized by a server group (cloud) connected to the medical image processing device 20 via a network NW.

[0012] The display 22 displays various information. For example, the display 22 displays a reference material image generated by the processing circuit 24. In addition, for example, the display 22 displays a GUI (Graphical User Interface) for receiving various instructions, settings, and the like from a user via the input interface 23. For example, the display 22 is a liquid crystal display or a CRT (Cathode Ray Tube) display. The display 22 may be a desktop type, or may be configured as a tablet terminal or the like capable of wireless communication with the medical image processing device 20 main body.

[0013] 1, the medical image processing device 20 is described as having the display 22, but the medical image processing device 20 may have a projector instead of or in addition to the display 22. The projector can project onto a screen, a wall, a floor, the body surface of the subject P, etc. under the control of the processing circuitry 24. As an example, the projector can also project onto any plane, object, space, etc. by projection mapping.

[0014] The input interface 23 receives various input operations from the user, converts the received input operations into electrical signals, and outputs the electrical signals to the processing circuit 24. For example, the input interface 23 is realized by a mouse, a keyboard, a trackball, a switch, a button, a joystick, a touchpad that performs input operations by touching the operation surface, a touch screen in which a display screen and a touchpad are integrated, a non-contact input circuit using an optical sensor, a voice input circuit, and the like. The input interface 23 may be configured as a tablet terminal or the like capable of wireless communication with the main body of the medical image processing device 20. The input interface 23 may also be a circuit that receives input operations from the user by motion capture. For example, the input interface 23 can receive the user's body movement, line of sight, and the like as input operations by processing signals acquired via a tracker and images collected about the user. The input interface 23 is not limited to only those that include physical operation parts such as a mouse and a keyboard. For example, an example of the input interface 23 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 medical image processing device 20 and outputs this electrical signal to the processing circuit 24.

[0015] The processing circuitry 24 controls the operation of the entire medical image processing device 20 by executing a control function 24a, a first generation function 24b, a specification function 24c, a second generation function 24d, an image processing function 24e, and an output function 24f. Here, the control function 24a and the second generation function 24d are an example of an acquisition unit. Also, the image processing function 24e is an example of an image processing unit. Also, the first generation function 24b is an example of a generation unit.

[0016] For example, the processing circuitry 24 reads out a program corresponding to the control function 24a from the memory 21 and executes it to control various functions such as a first generating function 24b, a specifying function 24c, a second generating function 24d, an image processing function 24e, and an output function 24f based on various input operations received from a user via the input interface 23. The control function 24a also controls reception of data via the network NW. For example, the control function 24a receives projection data collected by the X-ray CT device 10 via the network NW and stores the data in the memory 21.

[0017] Also, for example, the processing circuit 24 performs the generation processing of the reference material image by reading out from the memory 21 a program corresponding to the first generating function 24b and executing it. Also, for example, the processing circuit 24 performs the identification of the first X-ray energy and the second X-ray energy by reading out from the memory 21 a program corresponding to the identifying function 24c and executing it. Also, for example, the processing circuit 24 performs the generation processing of the monochromatic X-ray image by reading out from the memory 21 a program corresponding to the second generating function 24d and executing it. Also, for example, the processing circuit 24 performs the image processing of the monochromatic X-ray image by reading out from the memory 21 a program corresponding to the image processing function 24e and executing it. Also, for example, the processing circuit 24 outputs the reference material image generated by the first generating function 24b or various images generated based on the reference material image by reading out from the memory 21 a program corresponding to the output function 24f and executing it. Details of each function in the processing circuit 24 will be described later.

[0018] 1, each processing function is stored in the form of a program executable by a computer in the memory 21. The processing circuitry 24 is a processor that realizes a function corresponding to each program by reading and executing the program from the memory 21. In other words, the processing circuitry 24 in a state in which a program has been read has a function corresponding to the read program.

[0019] 1, the control function 24a, the first generation function 24b, the identification function 24c, the second generation function 24d, the image processing function 24e, and the output function 24f are realized by a single processing circuit 24. However, the processing circuit 24 may be configured by combining a plurality of independent processors, and each processor may execute a program to realize the functions. Also, each processing function of the processing circuit 24 may be realized by being appropriately distributed or integrated in a single or a plurality of processing circuits.

[0020] The processing circuitry 24 may also realize functions by using a processor of an external device connected via a network NW. For example, the processing circuitry 24 reads out and executes a program corresponding to each function from the memory 21, and realizes each function shown in FIG. 1 by using a server group (cloud) connected to the medical image processing device 20 via the network NW as a computational resource.

[0021] Next, the X-ray CT apparatus 10 will be described with reference to Fig. 2. Fig. 2 is a block diagram showing an example of the configuration of the X-ray CT apparatus 10 according to the first embodiment. For example, the X-ray CT apparatus 10 includes a gantry device 110, a bed device 130, and a console device 140.

[0022] In Fig. 2, the rotation axis of the rotating frame 113 in a non-tilted state or the longitudinal direction of the top board 133 of the bed device 130 is defined as the Z-axis direction. The axial direction that is perpendicular to the Z-axis direction and horizontal to the floor surface is defined as the X-axis direction. The axial direction that is perpendicular to the Z-axis direction and perpendicular to the floor surface is defined as the Y-axis direction. For the sake of explanation, Fig. 2 illustrates the gantry device 110 from multiple directions, and shows a case in which the X-ray CT device 10 has one gantry device 110.

[0023] The gantry device 110 includes an X-ray tube 111 , an X-ray detector 112 , a rotating frame 113 , an X-ray high voltage device 114 , a control device 115 , a wedge 116 , a collimator 117 , and a DAS (Data Acquisition System) 118 .

[0024] The X-ray tube 111 is a vacuum tube having a cathode (filament) that generates thermoelectrons and an anode (target) that generates X-rays upon impact of the thermoelectrons. The X-ray tube 111 generates X-rays to be irradiated onto the subject P by irradiating thermoelectrons from the cathode to the anode upon application of high voltage from the X-ray high voltage device 114.

[0025] The X-ray detector 112 detects X-rays irradiated from the X-ray tube 111 and passing through the subject P, and outputs a signal corresponding to the detected X-ray dose to the DAS 118. The X-ray detector 112 has, for example, a plurality of detection element rows in which a plurality of detection elements are arranged in a channel direction (channel direction) along an arc centered on the focal point of the X-ray tube 111. The X-ray detector 112 has, for example, a structure in which a plurality of detection element rows in which a plurality of detection elements are arranged in the channel direction are arranged in a row direction (slice direction, row direction).

[0026] For example, the X-ray detector 112 is an indirect conversion type detector having a grid, a scintillator array, and a photosensor array. The scintillator array has a plurality of scintillators. The scintillator has a scintillator crystal that outputs light with a photon amount corresponding to the amount of incident X-rays. The grid is disposed on the X-ray incident side of the scintillator array, and has an X-ray shielding plate that absorbs scattered X-rays. The grid may also be called a collimator (one-dimensional collimator or two-dimensional collimator). The photosensor array has a function of converting into an electrical signal corresponding to the amount of light from the scintillator, and has, for example, an optical sensor such as a photodiode. The X-ray detector 112 may be a direct conversion type detector having a semiconductor element that converts incident X-rays into an electrical signal.

[0027] The rotating frame 113 is an annular frame that supports the X-ray tube 111 and the X-ray detector 112 so as to face each other and rotates the X-ray tube 111 and the X-ray detector 112 by the control device 115. For example, the rotating frame 113 is a casting made of aluminum. The rotating frame 113 can further support the X-ray high voltage device 114, the wedge 116, the collimator 117, the DAS 118, and the like in addition to the X-ray tube 111 and the X-ray detector 112. Furthermore, the rotating frame 113 can further support various components not shown in FIG. 2. Hereinafter, the rotating frame 113 and a portion of the gantry device 110 that rotates together with the rotating frame 113 are also referred to as a rotating portion.

[0028] X-ray high voltage device 114 has electric circuits such as a transformer and a rectifier, and includes a high voltage generator that generates a high voltage to be applied to X-ray tube 111, and an X-ray control device that controls the output voltage according to the X-rays generated by X-ray tube 111. The high voltage generator may be of a transformer type or an inverter type. X-ray high voltage device 114 may be provided on rotating frame 113, or may be provided on a fixed frame (not shown).

[0029] The control device 115 has a processing circuit having a CPU (Central Processing Unit) and the like, and a driving mechanism such as a motor and an actuator. The control device 115 receives an input signal from the input interface 143 and controls the operation of the gantry device 110 and the bed device 130. For example, the control device 115 controls the rotation of the rotating frame 113, the tilt of the gantry device 110, the operation of the bed device 130, and the like. As an example, the control device 115 rotates the rotating frame 113 around an axis parallel to the X-axis direction according to input inclination angle (tilt angle) information as a control for tilting the gantry device 110. The control device 115 may be provided in the gantry device 110 or in the console device 140.

[0030] The wedge 116 is an X-ray filter for adjusting the amount of X-rays irradiated from the X-ray tube 111. Specifically, the wedge 116 is an X-ray filter that attenuates the X-rays irradiated from the X-ray tube 111 so that the X-rays irradiated from the X-ray tube 111 to the subject P have a predetermined distribution. For example, the wedge 116 is a wedge filter or a bow-tie filter, and is manufactured by processing aluminum or the like so as to have a predetermined target angle and a predetermined thickness.

[0031] The collimator 117 is a lead plate or the like for narrowing down the irradiation range of the X-rays transmitted through the wedge 116, and a slit is formed by combining a plurality of lead plates or the like. The collimator 117 may also be called an X-ray aperture. Also, while FIG. 2 shows a case where the wedge 116 is disposed between the X-ray tube 111 and the collimator 117, the collimator 117 may be disposed between the X-ray tube 111 and the wedge 116. In this case, the wedge 116 transmits and attenuates the X-rays that are emitted from the X-ray tube 111 and whose irradiation range is limited by the collimator 117.

[0032] The DAS 118 collects X-ray signals detected by each detection element of the X-ray detector 112. For example, the DAS 118 has an amplifier that performs an amplification process on the electric signal output from each detection element, and an A / D converter that converts the electric signal into a digital signal, and generates detection data. The DAS 118 is realized by, for example, a processor.

[0033] The data generated by the DAS 118 is transmitted by optical communication from a transmitter having a light emitting diode (LED) provided on the rotating frame 113 to a receiver having a photodiode provided on a non-rotating portion of the gantry 110 (e.g., a fixed frame, etc. (not shown in FIG. 2)), and then transferred to the console device 140. Here, the non-rotating portion is, for example, a fixed frame that rotatably supports the rotating frame 113. Note that the method of transmitting data from the rotating frame 113 to the non-rotating portion of the gantry 110 is not limited to optical communication, and any non-contact data transmission method or a contact data transmission method may be adopted.

[0034] The bed device 130 is a device on which the subject P to be scanned is placed and moved, and includes a base 131, a bed driving device 132, a top plate 133, and a support frame 134. The base 131 is a housing that supports the support frame 134 so that it can move in the vertical direction. The bed driving device 132 is a drive mechanism that moves the top plate 133 on which the subject P is placed in the longitudinal direction of the top plate 133, and includes a motor, an actuator, and the like. The top plate 133 is provided on the upper surface of the support frame 134, and is a plate on which the subject P is placed. Note that the bed driving device 132 may move the support frame 134 in the longitudinal direction of the top plate 133 in addition to the top plate 133.

[0035] The console device 140 includes a memory 141, a display 142, an input interface 143, and a processing circuit 144. Although the console device 140 will be described as being separate from the gantry device 110, the gantry device 110 may include the console device 140 or some of the components of the console device 140.

[0036] The memory 141 can be configured in the same manner as the above-mentioned memory 21. For example, the memory 141 stores various data collected from the subject P and stores a program for enabling a circuit included in the X-ray CT apparatus 10 to realize its function.

[0037] The display 142 can be configured in the same manner as the above-mentioned display 22. For example, the display 142 can display a reference material image generated in the medical image processing device 20 and a GUI for receiving various instructions and settings from a user under the control of the processing circuitry 144. Furthermore, the X-ray CT apparatus 10 may be provided with a projector instead of or in addition to the display 142.

[0038] The input interface 143 can be configured in the same manner as the above-described input interface 23. For example, the input interface 143 receives various input operations from a user, converts the received input operations into electrical signals, and outputs the electrical signals to the processing circuit 144.

[0039] The processing circuitry 144 controls the overall operation of the X-ray CT apparatus 10 by executing a control function 144a, an acquisition function 144b, and an output function 144c.

[0040] For example, the processing circuit 144 reads out a program corresponding to the control function 144a from the memory 141 and executes it to control various functions such as the collection function 144b and the output function 144c based on various input operations received from the user via the input interface 143.

[0041] Also, for example, the processing circuit 144 reads out a program corresponding to the collecting function 144b from the memory 141 and executes it to perform a scan on the subject P. For example, the collecting function 144b controls the X-ray high voltage device 114 to supply a high voltage to the X-ray tube 111. As a result, the X-ray tube 111 generates X-rays to be irradiated to the subject P. Also, the collecting function 144b controls the bed driving device 132 to move the subject P into the imaging opening of the gantry device 110. Also, the collecting function 144b adjusts the position of the wedge 116 and the opening degree and position of the collimator 117 to control the distribution of X-rays irradiated to the subject P. Also, the collecting function 144b rotates the rotating part by controlling the control device 115. Also, while the collecting function 144b is performing a scan, the DAS 118 collects X-ray signals from each detection element in the X-ray detector 112 and generates detection data.

[0042] Moreover, the collecting function 144b performs preprocessing on the detection data output from the DAS 118. For example, the collecting function 144b performs preprocessing such as logarithmic conversion processing, offset correction processing, inter-channel sensitivity correction processing, and beam hardening correction on the detection data output from the DAS 118. Note that data after preprocessing is also referred to as raw data. Moreover, the detection data before preprocessing and the raw data after preprocessing are collectively referred to as projection data.

[0043] Also, for example, the processing circuitry 144 reads out a program corresponding to the output function 144c from the memory 141 and executes it to output various data collected from the subject P. For example, the output function 144c transmits data collected by executing a scan on the subject P to the medical image processing apparatus 20 via the network NW. Also, for example, the output function 144c controls the display on the display 142.

[0044] 2, each processing function is stored in the memory 141 in the form of a program executable by a computer. The processing circuitry 144 is a processor that realizes a function corresponding to each program by reading and executing the program from the memory 141. In other words, the processing circuitry 144 in a state in which a program has been read has a function corresponding to the read program.

[0045] 2, the control function 144a, the collection function 144b, and the output function 144c are realized by a single processing circuit 144. However, the processing circuit 144 may be configured by combining a plurality of independent processors, and each processor may execute a program to realize the functions. Furthermore, each processing function of the processing circuit 144 may be realized by being appropriately distributed or integrated into a single or a plurality of processing circuits.

[0046] The processing circuitry 144 may also realize the functions by using a processor of an external device connected via a network NW. For example, the processing circuitry 144 reads out and executes a program corresponding to each function from the memory 141, and realizes each function shown in FIG. 2 by using a server group (cloud) connected to the X-ray CT device 10 via the network NW as a computational resource.

[0047] The above describes an example of the configuration of the medical image processing system 1 including the X-ray CT device 10 and the medical image processing device 20. With this configuration, the processing circuitry 24 in the medical image processing device 20 improves the image quality of the reference material image by the process described below.

[0048] First, a series of processes from collecting projection data from the subject P to generating a reference material image will be described with reference to Fig. 3. Fig. 3 is a diagram showing an example of the processes of the medical image processing system 1 according to the first embodiment. While a scan is being performed on the subject P, the DAS 118 generates projection data, and the processing circuitry 144 performs various processes such as pre-processing and separation processing on the generated projection data.

[0049] Here, the acquisition function 144b can execute a dual energy scan on the subject P. Dual energy is a technique for acquiring projection data corresponding to different X-ray energies. Although the dual energy method is not particularly limited, the acquisition function 144b can execute a dual energy scan by, for example, slow-kV switching, fast-kV switching, a stacked detector (dual layer), a dual source method, or a split method.

[0050] When performing dual energy collection using the slow-kV switching method, the collection function 144b performs a first scan using X-rays with energy E1, and then performs a second scan using X-rays with energy E2. The energy E2 is an X-ray energy different from the energy E1. For example, the collection function 144b can switch between the energy E1 and the energy E2 by controlling the X-ray high voltage device 114 and controlling the tube voltage supplied to the X-ray tube 111. This allows the collection function 144b to collect projection data corresponding to the energy E1 in the first scan, and collect projection data corresponding to the energy E2 in the second scan.

[0051] When dual energy acquisition is performed using the Fast-kV switching method, the acquisition function 144b changes the X-ray energy for each view during one scan, and acquires projection data corresponding to energy E1 and projection data corresponding to energy E2 substantially simultaneously. That is, during a scan, the X-ray tube 111 rotates around the subject P about the Z-axis shown in FIG. 2 as the rotation axis, and irradiates the subject P with X-rays while changing the irradiation angle. Here, the acquisition function 144b acquires projection data corresponding to energy E1 and projection data corresponding to energy E2 by switching the X-ray energy between energy E1 and energy E2 at high speed for each irradiation angle (view).

[0052] When performing dual energy collection in the dual layer method, the X-ray CT device 10 includes a stacked detector as the X-ray detector 112. For example, the X-ray detector 112 is composed of a first layer 112a and a second layer 112b, and detects X-rays irradiated from the X-ray tube 111 by dispersing them. For example, the first layer 112a detects X-rays of energy E1, and the second layer 112b detects X-rays of energy E2 that have passed through the first layer 112a. In this case, the collection function 144b can collect projection data corresponding to energy E1 based on the output from the first layer 112a, and collect projection data corresponding to energy E2 based on the output from the second layer 112b.

[0053] When performing dual energy collection using the dual source method, the X-ray CT device 10 includes a first X-ray tube 111a and a second X-ray tube 111b as the X-ray tube 111. The X-ray CT device 10 also includes a first X-ray detector 112c for detecting X-rays irradiated from the first X-ray tube 111a and a second X-ray detector 112d for detecting X-rays irradiated from the second X-ray tube 111b as the X-ray detector 112. In this case, the collection function 144b causes the first X-ray tube 111a to irradiate X-rays with energy E1 and the second X-ray tube 111b to irradiate X-rays with energy E2. This allows the collection function 144b to collect projection data corresponding to energy E1 based on the output from the first X-ray detector 112c and to collect projection data corresponding to energy E2 based on the output from the second X-ray detector 112d.

[0054] When performing dual energy collection using the split method, the X-ray CT device 10 includes a filter as the wedge 116 for splitting the X-rays irradiated from the X-ray tube 111 into a plurality of X-rays with different energies. For example, the X-ray CT device 10 includes an X-ray filter 116a and an X-ray filter 116b as the wedge 116. In this case, the collection function 144b can collect projection data corresponding to energy E1 based on the detection result of the X-rays irradiated from the X-ray tube 111 and transmitted through the X-ray filter 116a, and collect projection data corresponding to energy E2 based on the detection result of the X-rays irradiated from the X-ray tube 111 and transmitted through the X-ray filter 116b.

[0055] As described above, the acquisition function 144b executes a dual energy scan and acquires projection data corresponding to energy E1 and energy E2. The acquisition function 144b also performs pre-processing such as logarithmic conversion, offset correction, inter-channel sensitivity correction, and beam hardening correction on the acquired projection data. Furthermore, the acquisition function 144b performs separation processing on the pre-processed projection data.

[0056] Here, the separation process shown in FIG. 3 is, for example, a process of separating the projection data after pre-processing into projection data for each of a plurality of reference materials. Hereinafter, the projection data separated for each reference material is also referred to as line integral data. For example, the collection function 144b separates the projection data collected by a dual energy scan into line integral data for a first reference material and line integral data for a second reference material. The reference material is set from materials whose attenuation coefficients (linear attenuation coefficients and mass attenuation coefficients) at various energies are known. Although specific examples of the reference material are not particularly limited, the collection function 144b can set, for example, bone and water as the first reference material and the second reference material.

[0057] Such a separation process is based on the premise that the attenuation coefficient at a certain position of an imaging region at energy "E" can be expressed by the attenuation coefficients of each of two reference materials at energy "E" and the abundance ratios of each of the two reference materials present at that position. Here, the line integral of the abundance ratio "c1" of the first reference material and the line integral of the abundance ratio "c2" of the second reference material at X-ray transmission line "l" are respectively referred to as "first line integral data" and "second line integral data". In addition, the average attenuation coefficient of the first reference material at high energy, which is polychromatic, and the average attenuation coefficient of the second reference material are respectively referred to as "high energy first average attenuation coefficient" and "high energy second average attenuation coefficient". In addition, the average attenuation coefficient of the first reference material at low energy, which is polychromatic, and the average attenuation coefficient of the second reference material are respectively referred to as "low energy first average attenuation coefficient" and "low energy second average attenuation coefficient". In addition, the error due to beam hardening during high-energy irradiation of X-ray transmission line "l" and the error due to beam hardening during low-energy irradiation are referred to as "high-energy error" and "low-energy error", respectively.

[0058] The collecting function 144b approximates the high-energy projection data by an equation using the "high-energy first average attenuation coefficient", "first line integral data", "high-energy second average attenuation coefficient", "second line integral data", and "high-energy error". The collecting function 144b also approximates the low-energy projection data by an equation using the "low-energy first average attenuation coefficient", "first line integral data", "low-energy second average attenuation coefficient", "second line integral data", and "low-energy error". The collecting function 144b can then iteratively solve these two approximation equations to obtain the first line integral data and the second line integral data.

[0059] The output function 144c transmits the line integral data generated by the collection function 144b to the medical image processing device 20 via the network NW. The control function 24a receives the line integral data and stores it in the memory 21. The first generation function 24b executes a generation process of a reference material image based on the line integral data. That is, the first generation function 24b reconstructs a reference material image in which the pixel value of each pixel (pixel or voxel) indicates the presence rate of the reference material present in the pixel from the line integral data of each of the multiple reference materials.

[0060] For example, the first generating function 24b reconstructs a reference material image of the first reference material by performing back projection processing on the first line integral data. The first generating function 24b reconstructs a reference material image of the second reference material by performing back projection processing on the second line integral data. In the following, the reference material image of the first reference material will also be referred to as the first reference material image. In the following, the reference material image of the second reference material will also be referred to as the second reference material image. The pixel value of pixel "i" of the first reference material image is the abundance rate "c1" of the first reference material at pixel "i". In the second reference material image, the pixel value of pixel "i" of the second reference material image is the abundance rate "c2" of the second reference material at pixel "i".

[0061] Here, various image processing may be performed on the generated image to improve image quality. For example, various image processing such as noise reduction processing, contrast enhancement processing, edge enhancement processing, correction processing, etc. can be applied to an X-ray CT image in which CT value information is assigned to each pixel. However, unlike an X-ray CT image, a reference material image is not an image having CT value information, so image processing techniques related to X-ray CT images cannot be applied directly to a reference material image.

[0062] Therefore, as shown in Fig. 3, the processing circuitry 24 generates a monochromatic X-ray image based on the reference material image and performs image processing on the monochromatic X-ray image. Since the monochromatic X-ray image is an image having CT value information, it is possible to apply image processing techniques related to X-ray CT images. Furthermore, the processing circuitry 24 generates the reference material image again based on the monochromatic X-ray image after image processing. This allows the processing circuitry 24 to improve the image quality of the reference material image by utilizing image processing techniques related to X-ray CT images.

[0063] A series of processes including the generation process and image processing of a monochromatic X-ray image will be described below with reference to Fig. 4. Fig. 4 is a diagram showing a series of processes of the processing circuitry 24 according to the first embodiment. In Fig. 4, reference material images I11 and I12 will be described as examples of the first reference material image and the second reference material image. Also, in Fig. 4, a case where a monochromatic X-ray image I21 corresponding to the first X-ray energy and a monochromatic X-ray image I22 corresponding to the second X-ray energy are generated will be described.

[0064] For example, prior to the generation process of a monochromatic X-ray image, the specifying function 24c specifies the first X-ray energy and the second X-ray energy. For example, the specifying function 24c can specify the first X-ray energy and the second X-ray energy based on at least one of information on an imaging region or an imaging purpose.

[0065] For example, correspondence information that associates the imaging site and imaging purpose with the X-ray energy is generated in advance and stored in the memory 21. Such correspondence information may be generated by the identification function 24c, or correspondence information generated in an external device may be acquired via the network NW. Such correspondence information may also be manually created by a user. When performing the generation process of a monochromatic X-ray image, the identification function 24c acquires information on the imaging site and imaging purpose of the subject P and identifies the X-ray energy by comparing it with the correspondence information. For example, when the imaging site of the subject P is the "head" and the imaging purpose is "diagnosis of brain tumor", the identification function 24c identifies the first X-ray energy and the second X-ray energy by reading out the X-ray energy associated with "head / brain tumor" from the correspondence information.

[0066] The specifying function 24c can automatically acquire information on the imaging region and imaging purpose of the subject P from a system such as a Hospital Information System (HIS) or a Radiology Information System (RIS). The specifying function 24c can also acquire information on the imaging region and imaging purpose of the subject P based on an input operation by a user. Instead of the specifying function 24c specifying the X-ray energy, the user may manually set the first X-ray energy and the second X-ray energy.

[0067] Next, the second generating function 24d generates a monochromatic X-ray image I21 corresponding to the first X-ray energy and a monochromatic X-ray image I22 corresponding to the second X-ray energy based on the reference material image I11 and the reference material image I12. Hereinafter, the generating process of the monochromatic X-ray image based on the reference material image will be described with reference to formulas.

[0068] For example, the coordinates indicating the position of pixel "i" on the image as a pixel are "x" and "y". The pixel value (abundance rate of the first reference material) of the reference material image I11 at pixel "x, y" is "c1(x, y)", and the pixel value (abundance rate of the second reference material) of the reference material image I12 at pixel "x, y" is "c2(x, y)". The linear attenuation coefficient of the first reference material at any energy "E" is "μ1(E)". The linear attenuation coefficient of the second reference material at any energy "E" is "μ2(E)". In this case, the linear attenuation coefficient "μ(E, x, y)" of the imaging site corresponding to pixel "x, y" at energy "E" can be calculated by the following formula (1) using two reference material images.

[0069]

number

[0070] In addition, the CT value "CT♯(E,x,y)" of the imaging area corresponding to pixel "x,y" in "E" is calculated by substituting "μ(E,x,y)" calculated by formula (1) and the linear attenuation coefficient of water at "E" "μwater(E)" into the following formula (2).

[0071]

number

[0072] The second generating function 24d can generate a monochromatic X-ray image at any energy "E" by using the reference material image and formulas (1) and (2). That is, if two reference material images are acquired, the linear attenuation coefficient at any energy can be obtained from formula (1), and the CT value can be obtained by substituting this linear attenuation coefficient into formula (2). The second generating function 24d generates a monochromatic X-ray image by performing such processing for each pixel or each voxel.

[0073] For example, when "AkeV" is specified as the first X-ray energy and "BkeV" is specified as the second X-ray energy, the second generation function 24d generates a monochromatic X-ray image I21 corresponding to "AkeV" and a monochromatic X-ray image I22 corresponding to "BkeV." Note that "AkeV" is, for example, an X-ray energy higher than "BkeV."

[0074] Specifically, the second generation function 24d obtains the linear attenuation coefficient of pixel "x, y" in "AkeV" by using formula (1), and substitutes this linear attenuation coefficient and the linear attenuation coefficient of water in "AkeV" "μwater(A)" into formula (2) to calculate the CT value of pixel "i" to generate a monochromatic X-ray image I21. The second generation function 24d also obtains the linear attenuation coefficient of pixel "x, y" in "BkeV" by using formula (1), and substitutes this linear attenuation coefficient and the linear attenuation coefficient of water in "BkeV" "μwater(B)" into formula (2) to calculate the CT value of pixel "x, y" to generate a monochromatic X-ray image I22.

[0075] Next, the image processing function 24e executes image processing on the generated monochromatic X-ray image. Since each pixel of the monochromatic X-ray image has CT value information, various image processes using conventional CT value information can be applied to the monochromatic X-ray image. For example, as shown in Fig. 4, the image processing function 24e executes image processing A1 on the monochromatic X-ray image I21 and the monochromatic X-ray image I22 to generate the monochromatic X-ray image I31 and the monochromatic X-ray image I32. The image processing A1 is, for example, noise reduction processing, contrast enhancement processing, edge enhancement processing, correction processing, etc. using the CT value information.

[0076] Next, the first generating function 24b executes the reference material image generating process again using the monochromatic X-ray image I31 and the monochromatic X-ray image I32. That is, the first generating function 24b decomposes the monochromatic X-ray images into reference materials and generates reference material images for each of the reference materials. Hereinafter, the reference material image generating process based on the monochromatic X-ray images will be described with reference to formulas.

[0077] For example, the CT value "CT♯(A,x,y)" of pixel "x,y" of monochromatic X-ray image I31(AkeV) after image processing can be expressed by the following "upper formula of formula (3)" with "A" replacing "E" in formula (2). Also, the CT value "CT♯(B,x,y)" of pixel "x,y" of monochromatic X-ray image I32(BkeV) after image processing can be expressed by the following "lower formula of formula (3)" with "E" in formula (2) replaced by "B".

[0078]

number

[0079] Here, "μ(A,x,y)" in the upper formula of formula (3) indicates the linear attenuation coefficient at pixel "x,y" of monochromatic X-ray image I31 (AkeV). Also, "μ(B,x,y)" in the lower formula of formula (3) indicates the linear attenuation coefficient at pixel "x,y" of monochromatic X-ray image I32 (BkeV). Such linear attenuation coefficient reflects image processing A1 using CT value information.

[0080] When the upper formula of formula (3) is transformed into an equation for the linear attenuation coefficient "μ(A,x,y)" reflecting the image processing A1, it becomes the upper formula of the following formula (4). Also, when the lower formula of formula (3) is transformed into an equation for the linear attenuation coefficient "μ(B,x,y)" reflecting the image processing A1, it becomes the lower formula of the following formula (4).

[0081]

number

[0082] On the other hand, as described above, the linear attenuation coefficient of pixel "x, y" at any energy "E" is expressed by formula (1) using "c1(x, y)" and "c2(x, y)" and "μ1(E)" and "μ2(E)". Therefore, the linear attenuation coefficient "μ(A, x, y)" reflecting the image processing A1 can be expressed by the following "upper formula of formula (5)" in which "E" in formula (1) is replaced by "A". In addition, the linear attenuation coefficient "μ(B, x, y)" reflecting the image processing A1 can be expressed by the following "lower formula of formula (5)" in which "E" in formula (1) is replaced by "B".

[0083]

number

[0084] In the above formula (5), "c1(x,y)" is the abundance ratio of the first reference material at pixel "x,y" reflecting the image processing A1. Also, "c2(x,y)" in the above formula (5) is the abundance ratio of the second reference material at pixel "x,y" reflecting the image processing A1.

[0085] When the upper formula of formula (5) is transformed into an equation for the abundance rate "c1(x,y)" reflecting the image processing A1 of the first reference material, the upper formula of formula (6) is obtained. When the lower formula of formula (5) is transformed into an equation for the abundance rate "c2(x,y)" reflecting the image processing A1 of the second reference material, the lower formula of formula (6) is obtained.

[0086]

number

[0087] Here, the linear attenuation coefficient at any energy of the first reference material and the linear attenuation coefficient at any energy of the second reference material are known. That is, the first generation function 24b can preset the linear attenuation coefficients "μ1(A)" and "μ1(B)" at "A" and "B" of the first reference material, respectively, and the linear attenuation coefficients "μ2(A)" and "μ2(B)" at "A" and "B" of the second reference material, respectively, shown in formula (6).

[0088] In addition, the linear attenuation coefficient "μ(A,x,y)" reflecting the image processing A1 and the linear attenuation coefficient "μ(B,x,y)" reflecting the image processing A1 can be calculated by the formula (4) using the pixel values ​​of the monochromatic X-ray image I31 (AkeV) and the monochromatic X-ray image I32 (BkeV).

[0089] For this reason, the first generating function 24b performs the calculation process of formula (4) for each pixel using the monochromatic X-ray image I31 (AkeV) and the monochromatic X-ray image I32 (BkeV). Then, the first generating function 24b calculates the abundance ratio of each reference material reflecting the image processing A1 for each pixel by substituting the calculation process result using formula (4) into formula (6). As a result, the first generating function 24b decomposes the two monochromatic X-ray images into a reference material image I41 of the first reference material and a reference material image I42 of the second reference material. That is, the first generating function 24b can generate the reference material image I41 and the reference material image I42 based on the monochromatic X-ray image I31 and the monochromatic X-ray image I32 that have been subjected to the image processing A1.

[0090] The effect of image processing A1 is reflected in reference material image I41 and reference material image I42, and the image quality is improved compared to reference material image I11 and reference material image I12. That is, the processing circuitry 24 can improve the image quality of the reference material image by image processing using CT value information. In addition, various images such as monochromatic X-ray images, density images, and effective atomic number images can be further generated from the reference material image, and the processing circuitry 24 can also improve the image quality of various images generated based on the reference material image by image processing using CT value information.

[0091] In Fig. 4, the image processing A1 is described as being executed on both the monochromatic X-ray image I21 corresponding to the first X-ray energy and the monochromatic X-ray image I22 corresponding to the second X-ray energy. Here, it is preferable to optimize the type and parameters of the image processing depending on the processing target. Therefore, the processing circuitry 24 may perform different image processing on each of the multiple monochromatic X-ray images to further improve the image quality of the reference material image.

[0092] Hereinafter, a process in which different image processing is performed for each monochromatic X-ray image will be described with reference to Fig. 5. Fig. 5 is a diagram showing a series of processes of the processing circuit 24 according to the first embodiment. In Fig. 5, reference material image I13 and reference material image I14 will be described as examples of the first reference material image and the second reference material image. Also, in Fig. 5, a case in which a monochromatic X-ray image I23 corresponding to the first X-ray energy and a monochromatic X-ray image I24 corresponding to the second X-ray energy are generated will be described.

[0093] First, the specifying function 24c specifies the first X-ray energy and the second X-ray energy. For example, the specifying function 24c specifies the first X-ray energy and the second X-ray energy based on at least one of information on the imaging region and the imaging purpose. Alternatively, the user may manually set the first X-ray energy and the second X-ray energy in consideration of information on the imaging region, the imaging purpose, etc.

[0094] Next, the second generating function 24d generates a monochromatic X-ray image I23 corresponding to the first X-ray energy and a monochromatic X-ray image I24 corresponding to the second X-ray energy based on the reference material image I13 and the reference material image I14. For example, the second generating function 24d generates a monochromatic X-ray image I23 corresponding to "AkeV" and a monochromatic X-ray image I24 corresponding to "BkeV" using the above-mentioned formula (1) and formula (2). Note that the monochromatic X-ray image I23 is an example of a first monochromatic X-ray image. Also, the monochromatic X-ray image I24 is an example of a second monochromatic X-ray image.

[0095] Next, the image processing function 24e performs image processing on the generated monochromatic X-ray image. For example, as shown in FIG. 5, the image processing function 24e obtains a monochromatic X-ray image I33 by applying image processing A2 to the monochromatic X-ray image I23. The image processing function 24e obtains a monochromatic X-ray image I34 by applying image processing A3 to the monochromatic X-ray image I24. The image processing A2 is an example of a first image processing. The image processing A3 is an example of a second image processing. The monochromatic X-ray image I33 is an example of a first corrected monochromatic X-ray image. The monochromatic X-ray image I34 is an example of a second corrected monochromatic X-ray image.

[0096] Here, image processing A2 and image processing A3 are, for example, noise reduction processing, contrast enhancement processing, edge enhancement processing, correction processing, etc., using CT value information. Also, image processing A3 is an image processing different from image processing A2. For example, image processing A2 is a parameter processing corresponding to "AkeV", and image processing A3 is a parameter processing corresponding to "BkeV".

[0097] For example, the image processing A2 and the image processing A3 are image processing set in advance. As an example, image processing information in which the type of image processing, processing parameters, and X-ray energy are associated with each other is generated in advance and stored in the memory 21. Such image processing information may be generated by the image processing function 24e, or image processing information generated in an external device may be acquired via the network NW. Such image processing information may also be manually created by a user. When performing image processing, the identification function 24c acquires information on X-ray energy such as "AkeV" or "BkeV" and compares it with the image processing information to identify the image processing A2 and the image processing A3.

[0098] Here, the image processing A2 and the image processing A3 may be further associated with either the imaging site or the imaging purpose. As an example, the image processing A2 is an image processing in which parameters are adjusted to optimize noise reduction in a monochromatic X-ray image corresponding to "AkeV". Also, the image processing A3 is an image processing in which parameters are adjusted to optimize noise reduction in a monochromatic X-ray image corresponding to "BkeV".

[0099] Here, the image processing A2 and the image processing A3 are, for example, as follows when they are noise reduction processes. When a dual energy scan is performed as described above and projection data corresponding to energy E1 and energy E2 is collected, the energy and SD value (standard deviation value) of monochromatic X-rays created from the projection data according to the energies E1 and E2 typically form a downwardly convex graph as shown in FIG. 6. Noise reduction processing of monochromatic X-rays is performed at each energy (AkeV, BkeV). In this way, the image processing function 24e can perform noise reduction processing suitable for each monochromatic X-ray. Note that FIG. 6 is a diagram for explaining an example of image processing according to the first embodiment.

[0100] The image processing function 24e inputs the values ​​of input energies E1 and E2, and obtains information indicating the correspondence between the energy E_mono of the monochromatic X-ray corresponding to the pair of input energies (E1, E2) and the SD value. Furthermore, the image processing function 24e inputs each of the energies A [keV] and B [keV] of the monochromatic X-ray, and obtains the SD values ​​SD_A and SD_B corresponding to each monochromatic X-ray energy according to the information indicating the correspondence in FIG. 6. The image processing function 24e performs noise reduction processing on each monochromatic X-ray image using the values ​​of SD_A and SD_B. Furthermore, in such noise reduction processing, an intensity further corresponding to either the imaging site or the imaging purpose may be used as an input parameter.

[0101] In the above example, noise reduction processing was shown as an example of individual image processing for each monochromatic X-ray image, but this is not limited to the above, and individual contrast enhancement processing, edge enhancement processing, correction processing, etc. may also be applied to each monochromatic X-ray image.

[0102] In addition to or instead of the above examples, the image processing A2 and the image processing A3 may be image processing by a machine learning technique. For example, the image processing A2 may be a first processing using a model obtained by machine learning, and the image processing A3 may be a second processing using a model obtained by machine learning, different from the first processing. Here, the model used in the first processing and the model used in the second processing may be a common model or may be different models.

[0103] First, a case where the model used in the first process and the model used in the second process are the same will be described. For example, the image processing function 24e generates in advance a trained model M1 that is functionalized to reduce noise in an input image, or acquires in advance a trained model M1 that is generated in another device different from the medical image processing device 20.

[0104] A case where the image processing function 24e generates the trained model M1 will be described as an example. In this case, the image processing function 24e first acquires training data. For example, the image processing function 24e acquires a pair of a noisy first image and a high-quality second image as training data. For example, the first image and the second image are single-energy X-ray images collected at different doses. That is, the first image is an X-ray CT image collected using a low-dose X-ray, and the second image is an X-ray CT image collected using a high-dose X-ray. Next, the image processing function 24e inputs the noisy first image as input data and the high-quality second image as output data (target) to a machine learning engine such as a convolution neural network (CNN). Then, the image processing function 24e generates the trained model M1 by adjusting parameters so that the CNN that receives the input of the first image can output a favorable result. For example, a noise-reduced image is output from the output layer of the CNN that receives a first image as input, and the image processing function 24e adjusts the parameters of the CNN so as to minimize a function (error function) that represents the closeness between the noise-reduced image and a high-quality second image.

[0105] Although the first image on the input side is an X-ray CT image collected using low-dose X-rays, the embodiment is not limited to this. For example, the first image may be an image to which noise is added by a noise simulator or the like. Also, for example, the first image may be an image reconstructed by a Filtered Back Projection (FBP) method, and the second image may be an image reconstructed by a reconstruction method with higher accuracy than the FBP method (for example, an iterative reconstruction method). Also, the second image on the output side is a high-quality image, but the embodiment is not limited to this. For example, the second image may be a noisy image containing another noise independent of the first image. Also, although the learned model M1 is described as being a CNN, other types of machine learning engines may be adopted. For example, the learned model M1 may be a neural network such as a fully connected neural network or a recurrent neural network (RNN).

[0106] The trained model M1 is stored, for example, in the memory 21. The image processing function 24e can read out the trained model M1 from the memory 21 as needed and use it.

[0107] For example, the image processing function 24e applies the learned model M1 to the monochromatic X-ray image I23 to obtain a monochromatic X-ray image I23'. Next, the image processing function 24e obtains a monochromatic X-ray image I33 by combining the monochromatic X-ray image I23' and the monochromatic X-ray image I23 at a predetermined ratio. Note that the monochromatic X-ray image I23' is an example of a first processed image. Also, the ratio at which the monochromatic X-ray image I23' and the monochromatic X-ray image I23 are combined is an example of a first ratio.

[0108] Similarly, the image processing function 24e applies the learned model M1 to the monochromatic X-ray image I24 to obtain a monochromatic X-ray image I24'. Next, the image processing function 24e obtains a monochromatic X-ray image I34 by combining the monochromatic X-ray image I24' and the monochromatic X-ray image I24 at a predetermined ratio. Note that the monochromatic X-ray image I24' is an example of a second processed image. Also, the ratio at which the monochromatic X-ray image I24' and the monochromatic X-ray image I24 are combined is an example of a second ratio.

[0109] Here, the second ratio may be a ratio different from the first ratio. That is, the image processing A2 and the image processing A3 may be different image processing. For example, when the monochromatic X-ray image I23 corresponds to "AkeV" and the monochromatic X-ray image I24 corresponds to "BkeV" lower than "AkeV", the ratio of the monochromatic X-ray image I24' in the second ratio may be larger than the ratio of the monochromatic X-ray image I23' in the first ratio. That is, in general, the lower the energy, the higher the SD (Standard Deviation) in a monochromatic X-ray image. Therefore, by synthesizing the monochromatic X-ray image to which the trained model has been applied at a higher ratio as the energy decreases, a natural image can be obtained while obtaining the effect of noise reduction.

[0110] The trained model M1 may be generated for each part. For example, a trained model M11 that is functionalized to reduce noise in a monochromatic X-ray image collected about the head and a trained model M12 that is functionalized to reduce noise in a monochromatic X-ray image collected about the abdomen may be generated. In this case, the image processing function 24e can read out one of a plurality of trained models such as the trained model M11 or the trained model M12 according to the part of the subject P included in the monochromatic X-ray image I23 and the monochromatic X-ray image I24, and execute the image processing A2 and the image processing A3.

[0111] In addition, the trained model M1 may be generated for each imaging method. For example, a trained model M13 that is functionalized to reduce noise in a monochromatic X-ray image obtained by slow-kV switching and a trained model M14 that is functionalized to reduce noise in a monochromatic X-ray image obtained by fast-kV switching may be generated.

[0112] Here, it is known that the type of noise generated in the monochromatic X-ray image obtained by slow-kV switching is similar to that in the X-ray CT image collected by single energy. Therefore, as described above, the trained model M13 can be generated using the X-ray CT image collected by single energy as training data. For example, in the case of slow-kV switching, the monochromatic X-ray image I23 and the monochromatic X-ray image I24 are obtained based on the first scan data obtained by the first scan using X-rays corresponding to the first energy and the second scan data obtained by the second scan using X-rays corresponding to the second energy. In this case, the image quality can be further improved by using the trained model M13 obtained by machine learning using the X-ray CT image collected by single energy or the monochromatic X-ray image obtained by slow-kV switching as training data for the monochromatic X-ray image I23 and the monochromatic X-ray image I24. In addition, the trained model M14 can be generated, for example, by targeting monochromatic X-ray images obtained by slow-kV switching or X-ray CT images collected with single energy, and training a CNN or the like using monochromatic X-ray images obtained by fast-kV switching as input data.

[0113] In addition, although the trained model M1 functioned to reduce noise in the input image has been described above, the embodiment is not limited thereto. For example, other types of trained models such as trained model M2 functioned to improve the contrast of the input image and trained model M3 functioned to improve the resolution of the input image can be generated in the same manner and used when executing image processing A2 and image processing A3.

[0114] For example, the image processing function 24e can generate the learned model M2 by performing training such as CNN using an X-ray image collected by single energy or a monochromatic X-ray image obtained by any type of dual energy imaging as output data, and an image obtained by performing image processing to reduce the contrast of the image of the output data as input data. Also, for example, the image processing function 24e can generate the learned model M3 by performing training such as CNN using an X-ray image collected by single energy or a monochromatic X-ray image obtained by any type of dual energy imaging as output data, and an image obtained by performing image processing to reduce the resolution of the image of the output data (such as bundling multiple pixels) as input data.

[0115] Various trained models such as trained models M1 to M3 are appropriately selected according to the purpose of imaging and image quality requirements. For example, the user selects a requirement to be emphasized from among low noise, emphasis on contrast, and emphasis on resolution, and the image processing function 24e can select an appropriate trained model according to the selected requirement and execute image processing A2 and image processing A3. Note that, even when trained models M2 and M3 are used, the ratio of monochromatic X-ray images to which trained models have been applied to monochromatic X-ray images before the trained models have been applied can also be changed, as in the case of using trained model M1.

[0116] In addition, although the case where a common trained model is applied to the monochromatic X-ray image I23 and the monochromatic X-ray image I24 has been described, different trained models may be applied to the monochromatic X-ray image I23 and the monochromatic X-ray image I24, respectively. For example, when the monochromatic X-ray image I23 corresponds to "AkeV" and the monochromatic X-ray image I24 corresponds to "BkeV", the image processing function 24e may generate a trained model M15 corresponding to "AkeV" and a trained model M16 corresponding to "BkeV", respectively. For example, the trained model M15 can be generated by using a low-dose X-ray image collected by "AkeV" as input data and a high-dose X-ray image collected by "AkeV" as output data. Similarly, the trained model M16 can be generated by using a low-dose X-ray image collected by "BkeV" as input data and a high-dose X-ray image collected by "BkeV" as output data. Then, the image processing function 24e executes image processing A2 by applying the trained model M15 to the monochromatic X-ray image I23, and executes image processing A3 by applying the trained model M16 to the monochromatic X-ray image I24. In this case, the monochromatic X-ray image before the trained model is applied and the monochromatic X-ray image after the trained model is applied may not be combined.

[0117] In addition, the image processing A2 and the image processing A3 may be appropriately adjusted according to the user's request. For example, when the user performs an input operation to suppress noise reduction for the high-energy monochromatic X-ray image I23, the image processing function 24e performs low-intensity noise reduction processing as the image processing A2. When the user performs an input operation to suppress noise reduction for the low-energy monochromatic X-ray image I24, the image processing function 24e performs low-intensity noise reduction processing as the image processing A3. When the user performs an input operation to suppress noise more for the high-energy monochromatic X-ray image I23, the image processing function 24e performs high-intensity noise reduction processing as the image processing A2. When the user performs an input operation to suppress noise more for the low-energy monochromatic X-ray image I24, the image processing function 24e performs high-intensity noise reduction processing as the image processing A3.

[0118] Next, the first generating function 24b executes the reference material image generating process again based on the monochromatic X-ray image I33 and the monochromatic X-ray image I34. That is, the first generating function 24b decomposes the multiple monochromatic X-ray images for each reference material and generates a reference material image for each of the multiple reference materials. For example, the first generating function 24b generates the reference material image I43 and the reference material image I44 shown in FIG. 5 using the above-mentioned formulas (3) to (6). Note that the reference material image I43 and the reference material image I44 are examples of corrected reference material images.

[0119] Here, the second generating function 24d may further generate various images such as a monochromatic X-ray image, a density image, and an effective atomic number image based on the reference material image I43 and the reference material image I44. For example, the second generating function 24d can generate a monochromatic X-ray image based on the reference material image I43 and the reference material image I44 using the above-mentioned formula (1) and formula (2). Also, for example, the second generating function 24d can generate a density image, an effective atomic number image, etc. by performing various weighting calculations using the reference material image I43 and the reference material image I44. Also, the output function 24f displays the reference material image I43 and the reference material image I44, or various images generated based on the reference material image I43 and the reference material image I44 on the display 22.

[0120] The effects of the image processing A2 and the image processing A3 are reflected in the reference material image I43 and the reference material image I44, and the image quality is improved compared to the reference material image I13 and the reference material image I14. That is, the processing circuit 24 can improve the image quality of the reference material image by image processing using the CT value information. In particular, the image processing A2 and the image processing A3 are different image processing appropriately adjusted for the monochromatic X-ray image I23 and the monochromatic X-ray image I24, respectively, and a further improvement in the image quality of the reference material image is expected compared to the case where the same image processing is uniformly applied to the monochromatic X-ray image I23 and the monochromatic X-ray image I24. In addition, since the user can set different image processing for each of the monochromatic X-ray image I23 and the monochromatic X-ray image I24, the image quality of the reference material image can be adjusted with a higher degree of freedom. In addition, the processing circuit 24 can also improve the image quality of various images generated based on the reference material image I43 and the reference material image I44.

[0121] Note that image processing A2 and image processing A3 may be set with reference to various images generated based on the reference material image I43 and the reference material image I44. In the following, this point will be described using an example in which the first X-ray energy is "AkeV" and the second X-ray energy is "BkeV".

[0122] First, the second generating function 24d generates a monochromatic X-ray image I23 corresponding to "AkeV" and a monochromatic X-ray image I24 corresponding to "BkeV" based on the reference material image I13 and the reference material image I14. The image processing function 24e obtains a monochromatic X-ray image I33 by applying the image processing A2 corresponding to "AkeV" to the monochromatic X-ray image I23. The image processing function 24e obtains a monochromatic X-ray image I34 by applying the image processing A3 corresponding to "BkeV" to the monochromatic X-ray image I24. Next, the first generating function 24b generates a reference material image I43 and a reference material image I44 based on the monochromatic X-ray image I33 and the monochromatic X-ray image I34. Here, the second generating function 24d can further generate a monochromatic X-ray image corresponding to any X-ray energy based on the reference material image I43 and the reference material image I44. For example, the second generating function 24d can generate a monochromatic X-ray image I51 corresponding to "CkeV." For example, "CkeV" is a lower X-ray energy than "AkeV" and "BkeV."

[0123] In such a case, for example, when the user performs an input operation to suppress noise reduction for the monochromatic X-ray image I51, the image processing function 24e executes low-intensity noise reduction processing as the image processing A3. That is, the image processing function 24e can suppress noise reduction on the low energy side such as "CkeV" by suppressing noise reduction on the low energy side of "AkeV" and "BkeV". Alternatively, the image processing function 24e may suppress noise reduction in "CkeV" by suppressing noise reduction on both sides of "AkeV" and "BkeV".

[0124] Next, an example of the processing procedure by the medical image processing device 20 will be described with reference to FIG. 7. FIG. 7 is a flowchart for explaining a series of processing flows of the medical image processing device 20 according to the first embodiment. Steps S101 and S108 correspond to the control function 24a. Steps S102 and S106 correspond to the first generation function 24b. Step S103 corresponds to the identification function 24c. Step S104 corresponds to the second generation function 24d. Step S105 corresponds to the image processing function 24e. Step S107 corresponds to the output function 24f.

[0125] First, the processing circuitry 24 determines whether or not line integral data has been acquired from the X-ray CT device 10 (step S101), and enters a standby state if line integral data has not been acquired (step S101: No). On the other hand, if line integral data has been acquired (step S101: Yes), the processing circuitry 24 generates a reference material image I13 and a reference material image I14 based on the line integral data (step S102).

[0126] The processing circuitry 24 also specifies the first X-ray energy and the second X-ray energy (step S103). For example, the processing circuitry 24 specifies the first X-ray energy and the second X-ray energy based on at least one of information on the imaging site and imaging purpose. The process of step S103 may be executed before steps S101 and S102, or may be executed in parallel with steps S101 and S102. Instead of the processing circuitry 24 specifying the X-ray energy, the user may manually set the X-ray energy.

[0127] Next, the processing circuitry 24 generates a monochromatic X-ray image I23 corresponding to the first X-ray energy and a monochromatic X-ray image I24 corresponding to the second X-ray energy based on the reference material image I13 and the reference material image I14 (step S104). Next, the processing circuitry 24 executes the first image processing and the second image processing, respectively (step S105). For example, the processing circuitry 24 obtains a monochromatic X-ray image I33 by applying the image processing A2 corresponding to the first X-ray energy to the monochromatic X-ray image I23. Also, the processing circuitry 24 obtains a monochromatic X-ray image I34 by applying the image processing A3 corresponding to the second X-ray energy to the monochromatic X-ray image I24.

[0128] Next, the processing circuitry 24 generates a corrected reference material image (step S106). For example, the processing circuitry 24 generates a reference material image I43 and a reference material image I44 based on the monochromatic X-ray image I33 and the monochromatic X-ray image I34. The processing circuitry 24 also displays the generated reference material image I43 and reference material image I44 on the display 22 (step S107).

[0129] Next, the processing circuitry 24 determines whether or not to continue image processing (step S108). If image processing is to be continued (step S108: Yes), the processing circuitry 24 proceeds to step S103 again and specifies the X-ray energy. Here, the user may manually set the X-ray energy based on the result of referring to the corrected reference material image displayed in step S107. That is, the user may repeatedly execute a series of processes including image processing while adjusting the X-ray energy until a corrected reference material image suitable for diagnosis is generated. On the other hand, if image processing is not to be continued (step S108: No), the processing circuitry 24 ends the process.

[0130] As described above, according to the first embodiment, the second generating function 24d generates a first monochromatic X-ray image corresponding to the first X-ray energy and a second monochromatic X-ray image corresponding to the second X-ray energy. The image processing function 24e obtains a first corrected monochromatic X-ray image by applying a first image processing corresponding to the first X-ray energy to the first monochromatic X-ray image. The image processing function 24e obtains a second corrected monochromatic X-ray image by applying a second image processing different from the first image processing corresponding to the second X-ray energy to the second monochromatic X-ray image. The first generating function 24b generates a plurality of corrected reference material images based on the first corrected monochromatic X-ray image and the second corrected monochromatic X-ray image. As a result, the medical image processing apparatus 20 according to the first embodiment can improve the image quality of the reference material image by image processing using the CT value information.

[0131] As described above, the image processing function 24e applies different image processing to the first monochromatic X-ray image and the second monochromatic X-ray image. This allows the medical image processing device 20 according to the first embodiment to more effectively perform image processing using CT value information, thereby further improving the image quality of the reference material image. For example, the image processing function 24e selects an appropriate image processing method according to the dual energy imaging method as described above, thereby performing image processing more suited to each virtual monochromatic X-ray image, and thus obtaining the desired image quality for the reference material image.

[0132] As described above, the second generating function 24d can further generate various images such as a monochromatic X-ray image, a density image, and an effective atomic number image based on the multiple corrected reference material images. The medical image processing apparatus 20 according to the first embodiment can improve the image quality of the reference material images, thereby improving the image quality of the various images based on these reference material images.

[0133] Second Embodiment Although the first embodiment has been described above, the present invention may be embodied in various different forms in addition to the above-described embodiment.

[0134] For example, in the above embodiment, the collecting function 144b in the X-ray CT apparatus 10 is described as generating the line integral data, but the line integral data generating process may be performed in the medical image processing apparatus 20. For example, the collecting function 144b performs pre-processing on the projection data output from the DAS 118. The output function 144c transmits the pre-processed projection data to the medical image processing apparatus 20 via the network NW. Then, the first generating function 24b performs separation processing on the pre-processed projection data to generate line integral data, and generates reference material images such as the reference material image I13 and the reference material image I14 based on the line integral data.

[0135] As another example, the output function 144c transmits the projection data output from the DAS 118 to the medical image processing device 20 via the network NW. Next, the first generation function 24b performs various pre-processing on the projection data. Then, the first generation function 24b performs separation processing on the pre-processed projection data to generate line integral data, and generates reference material images such as the reference material image I13 and the reference material image I14 based on the line integral data.

[0136] In the above embodiment, the first generating function 24b is described as executing the generation process of the reference material image such as the reference material image I13 and the reference material image I14. That is, in the above embodiment, the first generating function 24b is described as executing the generation process of the reference material image to obtain a plurality of reference material images. However, the embodiment is not limited to this. For example, a plurality of reference material images may be generated in another device such as the X-ray CT device 10, and the control function 24a may obtain a plurality of reference material images via the network NW.

[0137] In the above-described embodiment, the second generation function 24d is described as executing the generation process of the monochromatic X-ray images such as the monochromatic X-ray image I23 and the monochromatic X-ray image I24. That is, in the above-described embodiment, the second generation function 24d is described as executing the generation process of the monochromatic X-ray images to obtain a first monochromatic X-ray image corresponding to the first X-ray energy and a second monochromatic X-ray image corresponding to the second X-ray energy. However, the embodiment is not limited to this. For example, the first monochromatic X-ray image and the second monochromatic X-ray image may be generated in another device such as the X-ray CT device 10, and the control function 24a may obtain the first monochromatic X-ray image and the second monochromatic X-ray image via the network NW.

[0138] In the above-described embodiment, the image generated in the processing circuit 24 is displayed on the display 22. However, the embodiment is not limited to this. For example, the output function 24f may transmit the corrected reference material image generated based on the first corrected monochromatic X-ray image and the second corrected monochromatic X-ray image to an external device such as the X-ray CT device 10, and the corrected reference material image may be displayed in the external device. For example, the output function 24f may transmit various images such as a density image generated based on the corrected reference material image to an external device such as the X-ray CT device 10, and the various images such as the density image may be displayed in the external device.

[0139] In addition, although the above embodiment has been described as an example of a dual energy case, the present invention can be similarly applied to a case where a multi-energy scan is performed. Multi-energy is a technique for collecting projection data corresponding to three or more different types of X-ray energy. For example, when N is a natural number equal to or greater than 3, the collection function 144b collects projection data corresponding to N types of X-ray energy. In this case, it is possible to set N types of reference materials and perform a process of generating a reference material image.

[0140] In the above-described embodiment, a first monochromatic X-ray image corresponding to a first X-ray energy and a second monochromatic X-ray image corresponding to a second X-ray energy are generated based on a plurality of reference material images. However, the embodiment is not limited to this. That is, the first monochromatic X-ray image and the second monochromatic X-ray image can be generated without using the reference material images.

[0141] As an example, the X-ray CT device 10 includes, as the X-ray detector 112, a photon-counting detector 112e that counts light derived from X-rays transmitted through the subject P. In this case, the collection function 144b executes a scan by fixing, for example, one type of tube voltage. The detector 112e outputs a signal capable of measuring the energy value of the X-ray photon every time an X-ray photon is incident. The DAS 118 discriminates the individual signals output from the detector 112e, and collects counting information including the incident position (detection position) of the X-ray photon and the energy value of the X-ray photon for each phase (tube phase) of the X-ray tube 111. That is, the DAS 118 collects counting information including the energy information of the X-ray photon as projection data.

[0142] When the photon-counting detector 112e is used, the second generating function 24d can generate a monochromatic X-ray image of any energy based on the projection data including the energy information of the X-ray photons. For example, the second generating function 24d reconstructs a first monochromatic X-ray image corresponding to a first X-ray energy based on the counting result of the X-ray photons corresponding to the first X-ray energy. Also, the second generating function 24d reconstructs a second monochromatic X-ray image corresponding to a second X-ray energy based on the counting result of the X-ray photons corresponding to the second X-ray energy. Note that the monochromatic X-ray image generated by the second generating function 24d when the photon-counting detector 112e is used may correspond to a specific energy value or a specific energy range (Bin).

[0143] In addition, the projection data collected using the photon-counting detector 112e can be separated for each X-ray energy based on the energy information. For example, when the photon-counting detector 112e is used, it is possible to obtain high-energy projection data and low-energy projection data, respectively, in the same manner as in the case of dual energy collection. Therefore, the first generating function 24b can generate a plurality of reference material images based on the projection data collected using the photon-counting detector 112e. In addition, the second generating function 24d can generate a first monochromatic X-ray image corresponding to the first X-ray energy and a second monochromatic X-ray image corresponding to the second X-ray energy based on the plurality of reference material images, as described above.

[0144] That is, the second generating function 24d can generate the first monochromatic X-ray image and the second monochromatic X-ray image based on the projection data obtained by the photon-counting detector 112e that counts the light derived from the X-ray individually. Alternatively, the reconstruction process of the first monochromatic X-ray image and the second monochromatic X-ray image may be performed in another device such as the X-ray CT device 10, and the control function 24a may acquire the first monochromatic X-ray image and the second monochromatic X-ray image via the network NW. Then, the image processing function 24e obtains the first corrected monochromatic X-ray image and the second corrected monochromatic X-ray image by applying the first image processing and the second image processing to the first monochromatic X-ray image and the second monochromatic X-ray image, respectively. In addition, the first generating function 24b generates a plurality of corrected reference material images based on the first corrected monochromatic X-ray image and the second corrected monochromatic X-ray image.

[0145] In the above embodiment, the processing circuitry 24 in the medical image processing device 20 executes various functions such as the control function 24a, the first generation function 24b, the identification function 24c, the second generation function 24d, the image processing function 24e, and the output function 24f. However, the embodiment is not limited to this. For example, the processing circuitry 144 in the X-ray CT device 10 may execute functions corresponding to the functions of the processing circuitry 24.

[0146] This point will be described below with reference to Fig. 8. Fig. 8 is a block diagram showing an example of the configuration of an X-ray CT apparatus 10 according to the second embodiment. The X-ray CT apparatus 10 shown in Fig. 8 differs from the X-ray CT apparatus 10 shown in Fig. 2 in that the processing circuitry 144 further includes a first generating function 144d, a specifying function 144e, a second generating function 144f, and an image processing function 144g.

[0147] The first generating function 144d is a function corresponding to the first generating function 24b. The identifying function 144e is a function corresponding to the identifying function 24c. The second generating function 144f is a function corresponding to the second generating function 24d. The image processing function 144g is a function corresponding to the image processing function 24e. Furthermore, the control function 144a and the second generating function 144f are an example of an acquisition unit. Furthermore, the image processing function 144g is an example of an image processing unit. Furthermore, the first generating function 144d is an example of a generating unit.

[0148] For example, the specifying function 144e specifies the first X-ray energy and the second X-ray energy based on at least one of information on an imaging region or an imaging purpose.

[0149] Also, for example, the collecting function 144b collects projection data by irradiating X-rays to the subject P. For example, the collecting function 144b executes a dual energy scan to collect projection data corresponding to a plurality of X-ray energies. Also, the collecting function 144b performs pre-processing and separation processing on the projection data to generate line integral data by separating the pre-processed projection data for each reference material. Next, the first generating function 144d generates a plurality of reference material images based on the line integral data. Next, the second generating function 144f generates a first monochromatic X-ray image and a second monochromatic X-ray image based on the plurality of reference material images. That is, the second generating function 144f executes a monochromatic X-ray image generation process to obtain a first monochromatic X-ray image corresponding to the first X-ray energy and a second monochromatic X-ray image corresponding to the second X-ray energy. Alternatively, a first monochromatic X-ray image and a second monochromatic X-ray image based on multiple reference material images may be generated in another device such as the medical image processing device 20, and the control function 144a may acquire the first monochromatic X-ray image and the second monochromatic X-ray image via the network NW.

[0150] As another example, the collecting function 144b executes a scan using the photon-counting detector 112e that counts light derived from X-rays individually, and collects projection data including energy information of X-ray photons. Also, for example, the second generating function 144f reconstructs a first monochromatic X-ray image corresponding to the first X-ray energy based on the counting result of X-ray photons corresponding to the first X-ray energy. Also, the second generating function 144f reconstructs a second monochromatic X-ray image corresponding to the second X-ray energy based on the counting result of X-ray photons corresponding to the second X-ray energy. Alternatively, the first monochromatic X-ray image and the second monochromatic X-ray image based on the photon-counting detector 112e may be generated in another device such as the medical image processing device 20, and the control function 144a may acquire the first monochromatic X-ray image and the second monochromatic X-ray image via the network NW.

[0151] Next, the image processing function 144g obtains a first corrected monochromatic X-ray image by applying a first image processing corresponding to the first X-ray energy to the first monochromatic X-ray image. Also, the image processing function 144g obtains a second corrected monochromatic X-ray image by applying a second image processing corresponding to the second X-ray energy, which is different from the first image processing, to the second monochromatic X-ray image. Next, the first generating function 144d generates a plurality of corrected reference material images based on the first corrected monochromatic X-ray image and the second corrected monochromatic X-ray image. Here, the second generating function 144f may further generate various images such as a monochromatic X-ray image, a density image, and an effective atomic number image based on the plurality of corrected reference material images.

[0152] Then, the output function 144c displays the corrected reference material image generated by the first generating function 144d and various images generated based on the corrected reference material image on the display 142. Alternatively, the output function 144c may transmit the images to an external device such as the medical image processing device 20 via the network NW instead of displaying them on the display 142. In this case, the corrected reference material image and various images generated based on the corrected reference material image are displayed on the display of the external device.

[0153] In the above-described embodiment, when the first image processing and the second image processing are image processing by machine learning, different models are applied to the first monochromatic X-ray image and the second monochromatic X-ray image, or the ratio of synthesis between the monochromatic X-ray image and the processed image obtained by applying a model to the monochromatic X-ray image is changed. However, the embodiment is not limited to this, and the first corrected monochromatic X-ray image and the second corrected monochromatic X-ray image may be obtained by applying a common model to the first monochromatic X-ray image and the second monochromatic X-ray image. For example, when the first monochromatic X-ray image and the second monochromatic X-ray image are reconstructed based on scan data obtained by a scan other than Fast-kV switching, the first corrected monochromatic X-ray image and the second corrected monochromatic X-ray image may be obtained by applying a common model obtained by machine learning to the first monochromatic X-ray image and the second monochromatic X-ray image.

[0154] In the above-described embodiment, an example has been described in which a model obtained by machine learning is applied to a monochromatic X-ray image obtained by a multi-energy scan such as a dual energy scan. However, the embodiment is not limited to this. For example, a model obtained by machine learning may be applied to an X-ray CT image obtained by a non-multi-energy scan. For example, a common model obtained by machine learning may be applied to the above-described first monochromatic X-ray image and second monochromatic X-ray image, and an X-ray CT image obtained by a non-multi-energy scan.

[0155] The term "processor" used in the above description means a circuit such as a CPU, a GPU (Graphics Processing Unit), an Application Specific Integrated Circuit (ASIC), a programmable logic device (e.g., a Simple Programmable Logic Device (SPLD), a Complex Programmable Logic Device (CPLD), and a Field Programmable Gate Array (FPGA)). When the processor is, for example, a CPU, the processor realizes a function by reading and executing a program stored in a memory circuit. On the other hand, when the processor is, for example, an ASIC, instead of storing a program in a memory circuit, the function is directly incorporated as a logic circuit in the circuit of the processor. Note that each processor in the embodiment is not limited to being configured as a single circuit for each processor, but may be configured as one processor by combining multiple independent circuits to realize the function. Furthermore, multiple components in each figure may be integrated into one processor to realize the function.

[0156] 1, a single memory 21 is described as storing a program corresponding to each processing function of the processing circuit 24. In addition, in FIG. 2 and FIG. 8, a single memory 141 is described as storing a program corresponding to each processing function of the processing circuit 144. However, the embodiment is not limited to this. For example, a configuration may be adopted in which a plurality of memories 21 are distributed and the processing circuit 24 reads out the corresponding program from each memory 21. Similarly, a configuration may be adopted in which a plurality of memories 141 are distributed and the processing circuit 144 reads out the corresponding program from each memory 141. In addition, instead of storing the program in the memory 21 or the memory 141, the program may be directly built into the circuit of the processor. In this case, the processor realizes the function by reading and executing the program built into the circuit.

[0157] Each component of each device according to the above-mentioned embodiment is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or a part of them can be functionally or physically distributed and integrated in any unit according to various loads, usage conditions, etc. Furthermore, each processing function performed by each device can be realized in whole or in any part by a CPU and a program analyzed and executed by the CPU, or can be realized as hardware using wired logic.

[0158] The medical image processing method described in the above-mentioned embodiment can be realized by executing a prepared medical image processing program on a computer such as a personal computer or a workstation. This medical image processing program can be distributed via a network such as the Internet. This medical image processing program can also be recorded on a non-transitory recording medium readable by a computer such as a hard disk, a flexible disk (FD), a CD-ROM, an MO, or a DVD, and executed by being read from the recording medium by a computer.

[0159] According to at least one of the embodiments described above, the image quality of the reference material image can be improved.

[0160] Although some embodiments have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, modifications, and combinations of embodiments can be made without departing from the spirit of the invention. These embodiments and their modifications are included in the scope of the invention and its equivalents as described in the claims, as well as the scope and spirit of the invention. [Explanation of symbols]

[0161] 1 Medical image processing system 10 X-ray CT device 140 Console device 144 Processing Circuit 144a Control Functions 144b Collection function 144c Output Function 144d 1st generation function 144e Specific Functions 144f Second generation function 144g Image processing function 20 Medical image processing device 24 Processing circuit 24a Control Functions 24b 1st generation function 24c Specific functions 24d 2nd generation function 24e Image processing function 24f output function

Claims

1. acquiring a first monochromatic x-ray image corresponding to a first x-ray energy and a second monochromatic x-ray image corresponding to a second x-ray energy; applying a first image processing to the first monochromatic X-ray image, the first image processing corresponding to either the imaging region or the imaging purpose and the first X-ray energy, to obtain a first corrected monochromatic X-ray image; applying a second image processing to the second monochromatic X-ray image, the second image processing being different from the first image processing and corresponding to either the imaging region or the imaging purpose and the second X-ray energy, to the second monochromatic X-ray image to obtain a second corrected monochromatic X-ray image; generating a plurality of corrected reference material images based on the first corrected monochromatic x-ray image and the second corrected monochromatic x-ray image.

2. generating a plurality of reference material images based on the projection data corresponding to a plurality of different X-ray energies; The medical image processing method according to claim 1 , further comprising generating the first monochromatic X-ray image and the second monochromatic X-ray image based on the plurality of reference material images.

3. Collecting the projection data by irradiating an object with X-rays; generating the plurality of reference material images based on the projection data; The medical image processing method according to claim 2 , further comprising generating the first monochromatic X-ray image and the second monochromatic X-ray image based on the plurality of reference material images.

4. 2. The medical image processing method according to claim 1, wherein the first monochromatic X-ray image and the second monochromatic X-ray image are generated based on projection data obtained by a photon-counting detector that individually counts light originating from X-rays.

5. Identifying the first X-ray energy and the second X-ray energy based on at least one of information on an imaging region or an imaging purpose; 5. The medical image processing method according to claim 2, further comprising generating the first monochromatic X-ray image corresponding to the first X-ray energy and the second monochromatic X-ray image corresponding to the second X-ray energy.

6. The first image processing is a first processing using a model obtained by machine learning and configured to improve the image quality of an input image, The medical image processing method according to any one of claims 1 to 5, wherein the second image processing is a second processing different from the first processing, using a model different from the model obtained by machine learning and functioned to improve the image quality of the input image.

7. the first image processing is a process of obtaining the first corrected monochromatic X-ray image by combining a first processed image obtained by applying a model obtained by machine learning, which is functionalized to improve image quality of an input image, to the first monochromatic X-ray image at a first ratio with the first monochromatic X-ray image; The medical image processing method according to any one of claims 1 to 5, wherein the second image processing is a process of obtaining the second corrected monochromatic X-ray image by combining a second processed image obtained by applying the model to the second monochromatic X-ray image with the second monochromatic X-ray image at a second ratio different from the first ratio.

8. 8. The medical image processing method of claim 7, wherein when the first X-ray energy is higher than the second X-ray energy, a proportion of the second processed image in the second ratio is greater than a proportion of the first processed image in the first ratio.

9. 9. The medical image processing method according to claim 1, wherein the first monochromatic X-ray image and the second monochromatic X-ray image are obtained based on first scan data obtained in a first scan using X-rays corresponding to the first X-ray energy and second scan data obtained in a second scan using X-rays corresponding to the second X-ray energy.

10. The medical image processing method according to any one of claims 1 to 8, wherein the first monochromatic X-ray image and the second monochromatic X-ray image are obtained based on scan data obtained by a scan that does not employ fast-kV switching.

11. an acquisition unit that acquires a first monochromatic X-ray image corresponding to a first X-ray energy and a second monochromatic X-ray image corresponding to a second X-ray energy; an image processing unit that applies a first image processing corresponding to either the imaging region or the imaging purpose and the first X-ray energy to the first monochromatic X-ray image to obtain a first corrected monochromatic X-ray image, and applies a second image processing different from the first image processing corresponding to either the imaging region or the imaging purpose and the second X-ray energy to the second monochromatic X-ray image to obtain a second corrected monochromatic X-ray image; a generating unit that generates a plurality of corrected reference material images based on the first corrected monochromatic X-ray image and the second corrected monochromatic X-ray image; A medical image processing device comprising:

12. The first image processing is a first processing using a model obtained by machine learning and configured to improve the image quality of an input image, The medical image processing device according to claim 11 , wherein the second image processing is a second processing different from the first processing, using a model different from the model obtained by machine learning and functioned to improve the image quality of the input image.

13. the first image processing is a process of obtaining the first corrected monochromatic X-ray image by combining a first processed image obtained by applying a model obtained by machine learning, which is functionalized to improve image quality of an input image, to the first monochromatic X-ray image at a first ratio with the first monochromatic X-ray image; 12. The medical image processing device according to claim 11, wherein the second image processing is a process of obtaining the second corrected monochromatic X-ray image by combining a second processed image obtained by applying the model to the second monochromatic X-ray image and the second monochromatic X-ray image at a second ratio different from the first ratio.

14. The medical image processing device of claim 13 , wherein when the first X-ray energy is higher than the second X-ray energy, a proportion of the second processed image in the second ratio is greater than a proportion of the first processed image in the first ratio.

15. The medical image processing device according to any one of claims 11 to 14, wherein the first monochromatic X-ray image and the second monochromatic X-ray image are obtained based on first scan data obtained in a first scan using X-rays corresponding to the first X-ray energy and second scan data obtained in a second scan using X-rays corresponding to the second X-ray energy.

16. The medical image processing device according to any one of claims 11 to 14, wherein the first monochromatic X-ray image and the second monochromatic X-ray image are obtained based on scan data obtained by a scan that does not employ fast-kV switching.

17. The acquisition unit further acquires an X-ray CT image obtained by a non-multi-energy scan, The medical image processing device according to any one of claims 11 to 16, wherein the image processing unit applies a common model obtained by machine learning to the first monochromatic X-ray image, the second monochromatic X-ray image, and the X-ray CT image, the model being configured to improve the image quality of an input image.

18. an acquisition unit that acquires a first monochromatic X-ray image corresponding to a first X-ray energy and a second monochromatic X-ray image corresponding to a second X-ray energy; an image processing function for obtaining a first corrected monochromatic X-ray image by applying a first image processing corresponding to either the imaging region or the imaging purpose and the first X-ray energy to the first monochromatic X-ray image, and for obtaining a second corrected monochromatic X-ray image by applying a second image processing different from the first image processing corresponding to either the imaging region or the imaging purpose and the second X-ray energy to the second monochromatic X-ray image; a generating unit that generates a plurality of corrected reference material images based on the first corrected monochromatic X-ray image and the second corrected monochromatic X-ray image; An X-ray CT apparatus comprising:

Images