CT systems and storage media

Abstract

We provide a technology that can generate virtual monochromatic X-ray images of various energies (keV). The CT system includes: reconstructing a first CT image 31 based on data obtained by scanning a subject under a scan condition in which a first tube voltage (120 kV) is applied to an X-ray tube; inferring a virtual monochromatic X-ray image 32 of a second energy (50 keV) different from a first energy (70 keV) corresponding to the first tube voltage based on the first CT image; and calculating a first CT number (v) corresponding to the first energy. i ) as a reference, the second CT value (v j ) and the third CT value (v k ) based on a first coefficient (scaling coefficient a) that defines the relationship between the CT value (v k ) is determined.

Description

[Technical Field]

[0001] The present invention relates to a CT system for generating a virtual monochromatic X-ray image of an object (such as a subject), and to a storage medium having stored thereon instructions for generating a virtual monochromatic X-ray image of the object. [Background technology]

[0002] CT scanners are known as medical devices that non-invasively image a subject. CT scanners are widely used in hospitals and other medical facilities because they can obtain cross-sectional images of a subject in a short scanning time.

[0003] A CT system applies a predetermined voltage to the cathode-anode tube of an X-ray tube to generate X-rays. The generated X-rays pass through the subject and are detected by a detector. The CT system reconstructs a CT image of the subject based on the data detected by the detector. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 6031618 Summary of the Invention [Problem to be solved by the invention]

[0005] SECT (Single Energy CT) is a well-known imaging technique for CT devices. SECT is a method of generating X-rays by applying a predetermined voltage (e.g., 120 kVp) to the cathode-anode tube of an X-ray tube to obtain a CT image of the subject. However, with SECT, different substances can have similar CT values, making it difficult to identify the different substances.

[0006] Therefore, research and development has been conducted on DECT (Dual Energy CT) technology. DECT is a technology that uses X-rays in different energy ranges to distinguish materials, and DECT-compatible CT devices are also commercially available. DECT technology has a wide range of applications, and can be used, for example, to reconstruct virtual monochromatic X-ray images of each energy.

[0007] However, many medical institutions have not yet installed DECT-compatible CT scanners. Therefore, research and development is being conducted on technology that uses deep learning to infer virtual monochromatic X-ray images from images acquired by SECT, so that even medical institutions that do not have DECT-compatible CT scanners can provide diagnoses using virtual monochromatic X-ray images.

[0008] For example, a technology has been developed that infers a 50 keV image based on an image obtained when a 120 kV tube voltage is applied to an X-ray tube. This technology uses a trained neural network created using AI technology to infer a 50 keV virtual monochromatic X-ray image. This trained neural network is created, for example, as follows:

[0009] To create such a trained neural network, a large amount of training data using 120 kV CT images and 50 keV virtual monochromatic X-ray images is prepared, and the neural network is trained using this training data. This training allows for the creation of a trained neural network that can infer 50 keV virtual monochromatic X-ray images from 120 kV CT images. The trained neural network created in this way can infer 50 keV virtual monochromatic X-ray images from 120 kV CT images obtained using single-energy technology. It is known that CT images obtained using a 120 kV tube voltage generally exhibit characteristics similar to those of 70 kV virtual monochromatic X-ray images, although this depends on the type of CT device. Therefore, by inferring a 50 keV virtual monochromatic X-ray image using a trained neural network, users can compare 120 kV CT images (70 keV virtual monochromatic X-ray images) with 50 keV virtual monochromatic X-rays. This can be expected to improve diagnostic performance.

[0010] Although the above technology can only infer images of 50 keV, it is expected that if images of keV other than 50 keV can also be inferred, this will further contribute to improving diagnostic performance. For example, by creating a trained neural network that infers images of keV other than 50 keV in addition to a trained neural network that infers images of 50 keV, it will be possible to infer not only images of 50 keV but also images of keV other than 50 keV, which is expected to further contribute to improving diagnostic performance.

[0011] However, with the above method, it is necessary to create a trained neural network for each virtual monochromatic X-ray image of each energy. Therefore, it is necessary to prepare training data for each virtual monochromatic X-ray image of the energy to be inferred and train the neural network. This poses the problem of increased development man-hours.

[0012] Therefore, there is a need for a technology that can generate virtual monochromatic X-ray images of various energies with minimal development effort. [Means for solving the problem]

[0013] A first aspect of the present invention is a CT system, comprising: an X-ray tube to which a tube voltage is applied; one or more processors, reconstructing a first CT image based on data obtained by scanning the subject under a scan condition in which a first tube voltage is applied to the X-ray tube; deducing a virtual monochromatic X-ray image of a second energy different from a first energy corresponding to the first tube voltage based on the first CT image; determining a CT number of the virtual monochromatic X-ray image of the third energy based on a first coefficient that defines a relationship between a second CT number corresponding to the second energy and a third CT number corresponding to a third energy, with a first CT number corresponding to the first energy as a reference; and one or more processors executing CT system, including

[0014] Also, a second aspect of the present invention provides one or more non-transitory computer-readable storage media having stored thereon instructions, the instructions, when executed by the one or more processors, causing the one or more processors to: reconstructing a first CT image based on data obtained by scanning the subject under a scan condition in which a first tube voltage is applied to the X-ray tube; deducing a virtual monochromatic X-ray image of a second energy different from a first energy corresponding to the first tube voltage based on the first CT image; determining a CT number of the virtual monochromatic X-ray image of the third energy based on a first coefficient that defines a relationship between a second CT number corresponding to the second energy and a third CT number corresponding to a third energy, with a first CT number corresponding to the first energy as a reference; It is a storage medium that causes the device to perform operations including the above. [Effects of the Invention]

[0015] In the present invention, a virtual monochromatic X-ray image of any energy (e.g., 40 keV) desired by a user can be calculated by using a first coefficient that defines the relationship between a second CT number corresponding to the second energy and a third CT number corresponding to a third energy, based on a first CT number corresponding to the first energy. Therefore, since it is not necessary to create a trained neural network for each virtual monochromatic X-ray image of each energy, the number of development steps can be reduced, and development costs can be significantly reduced. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a block diagram of a CT system 100 according to a first embodiment. [Figure 2] FIG. 1 is a schematic diagram of a curve showing the change in CT value relative to energy (keV). [Figure 3] FIG. 1 is an explanatory diagram of a method for creating a curve 12. [Figure 4] FIG. 1 shows curve 12. [Figure 5] The position of 50 keV is indicated by a dashed line 22. [Figure 6] The position of 40 keV is indicated by a dashed line 23. [Figure 7] FIG. 1 is an explanatory diagram of the relationship between CT values. [Figure 8] FIG. 11 is an explanatory diagram of the relationship of the CT value of the curve 11. [Figure 9] FIG. 10 is an explanatory diagram for calculating the CT value of a 45 keV virtual monochromatic X-ray image. [Figure 10] FIG. 2 is an explanatory diagram of a lookup table LUT1 stored in a storage device. [Figure 11] FIG. 1 is a flow diagram for acquiring a virtual monochromatic X-ray image of an object at any energy. [Figure 12] FIG. 1 is a diagram schematically illustrating a CT image 31 acquired by scanning a subject. [Figure 13]FIG. 1 shows a schematic diagram of an inferred 50 keV virtual monochromatic X-ray image 32. [Figure 14] FIG. 1 is an illustration of the equations used to create a 40 keV virtual monochromatic x-ray image. [Figure 15] FIG. 10 is an explanatory diagram for calculating a CT value v40 using equation (9). [Figure 16] FIG. 10 is a flowchart of step ST3 in the second embodiment. [Figure 17] FIG. 10 is an explanatory diagram of step ST3. [Figure 18] FIG. 1 is an explanatory diagram of a problem that occurs when a subject is scanned at a tube voltage of 100 kV. [Figure 19] FIG. 10 is an explanatory diagram of the principle of generating a 50 keV virtual monochromatic X-ray image from a 100 kV CT image in the third embodiment. [Figure 20] FIG. 10 is an explanatory diagram of a lookup table LUT2 stored in a storage device. [Figure 21] FIG. 1 is a flow diagram for acquiring a 50 keV virtual monochromatic X-ray image. [Figure 22] FIG. 22 is an explanatory diagram of the flow of FIG. 21. DETAILED DESCRIPTION OF THE INVENTION

[0017] Hereinafter, a description will be given of an embodiment of the invention, but the present invention is not limited to the following embodiment.

[0018] FIG. 1 is a block diagram of a CT system 100 according to the first embodiment. The CT system 100 includes a gantry 102. The gantry 102 has an opening into which a subject (image subject) 112 moves, and the subject 112 is scanned.

[0019] The gantry 102 is equipped with an X-ray tube 104, a filter unit 103, a pre-collimator 105, an X-ray detector 108, and the like.

[0020] The X-ray tube 104 generates X-rays when a predetermined voltage is applied to the cathode-anode tube. The filter section 103 includes, for example, a flat plate filter and / or a bowtie filter. The pre-collimator 105 is a member for narrowing down the irradiation range of X-rays so that unnecessary areas are not irradiated with X-rays.

[0021] The X-ray detector 108 includes a plurality of detector elements 202. The plurality of detector elements 202 detects the X-ray beam 106 emitted from the X-ray tube 104 and passing through an object 112, such as a patient. Thus, the X-ray detector 108 can acquire projection data for each view.

[0022] Projection data detected by the X-ray detector 108 is collected by the DAS 214. The DAS 214 performs predetermined processing on the collected projection data, including sampling and digital conversion. The processed projection data is sent to the computer 216. The computer 216 stores the data from the DAS 214 in the storage device 218. The storage device 218 includes one or more storage media that store programs, instructions to be executed by a processor, and the like. The storage medium may be, for example, one or more non-transitory computer-readable storage media. The storage device 218 may include, for example, a hard disk drive, a floppy disk drive, a compact disk read / write (CD-R / W) drive, a digital versatile disk (DVD) drive, a flash drive, and / or a solid-state storage drive.

[0023] The computer 216 includes one or more processors that are used by the computer 216 to output commands and parameters to the DAS 214, the X-ray controller 210, and / or the gantry motor controller 212 to control system operations such as data acquisition and / or processing.

[0024] An operator console 220 is coupled to the computer 216. An operator can operate the operator console 220 to enter predetermined operator inputs related to the operation of the CT system 100 into the computer 216. The computer 216 receives operator inputs, including commands and / or scan parameters, via the operator console 220 and controls system operation based on the operator inputs. The operator console 220 can include a keyboard (not shown) or a touch screen for the operator to enter commands and / or scan parameters.

[0025] The X-ray controller 210 controls the X-ray tube 104 based on control signals from the computer 216. The gantry motor controller 212 also controls the gantry motor based on control signals from the computer 216.

[0026] Although FIG. 1 shows only one operator console 220 , more than one operator console may be coupled to computer 216 .

[0027] CT system 100 may also be coupled to multiple remotely located displays, printers, workstations, and / or similar devices, for example, via wired and / or wireless networks.

[0028] In one embodiment, for example, CT system 100 may include or be coupled to a picture archiving and communication system (PACS) 224. In an exemplary implementation, PACS 224 may be coupled to a remote system, such as a radiology department information system, a hospital information system, and / or an internal or external network (not shown).

[0029] The computer 216 provides commands to the table motor controller 118 for controlling the table 116. The table motor controller 118 can control the table 116 based on the received commands. In particular, the table motor controller 118 can move the table 116 so that the subject 112 is properly positioned within the opening of the gantry 102.

[0030] As described above, DAS 214 samples and digitally converts projection data acquired by detector elements 202. Image reconstructor 230 then reconstructs an image using the sampled and digitally converted data. Image reconstructor 230 includes one or more processors that may perform the image reconstruction processing. While image reconstructor 230 is shown in FIG. 1 as a separate component from computer 216, image reconstructor 230 may form part of computer 216. Computer 216 may also perform one or more functions of image reconstructor 230. Furthermore, image reconstructor 230 may be located remotely from CT system 100 and operatively connected to CT system 100 using a wired or wireless network.

[0031] Image reconstructor 230 may store the reconstructed image in storage device 218. Image reconstructor 230 may also transmit the reconstructed image to computer 216. Computer 216 may transmit the reconstructed image and / or patient information to a display 232 communicatively coupled to computer 216 and / or image reconstructor 230.

[0032] The various methods and processes described herein can be stored as executable instructions on a non-transitory storage medium within CT system 100 or on an external storage medium communicatively connected to CT system 100. The executable instructions can be stored on a single storage medium or can be distributed across multiple storage media. One or more processors included in CT system 100 execute the various methods, steps, and processes described herein in accordance with the instructions stored on the storage medium. For example, in this embodiment, the processor(s) execute methods, steps, and processes related to trained neural network 30 (which is a neural network that infers a 50 keV virtual monochromatic X-ray image from a 120 kV CT image; see, e.g., FIGS. 13 and 15 ), described below. The CT system 100 is configured as described above.

[0033] As described above, the CT system 100 can use the trained neural network 30. The trained neural network 30 is a neural network that infers a 50 keV virtual monochromatic X-ray image from a 120 kV CT image. A neural network that infers a 50 keV virtual monochromatic X-ray image from a 120 kV CT image is known and is implemented in some CT systems available from GE Healthcare, for example, under the name "True Enhance DL." As described above, the trained neural network 30 can infer a 50 keV virtual monochromatic X-ray image from a 120 kV CT image. Therefore, even in CT systems that do not incorporate dual-energy technology, a 50 keV virtual monochromatic X-ray image can be obtained from a 120 kV CT image obtained by scanning a subject, which is expected to improve diagnostic performance.

[0034] Furthermore, although the trained neural network 30 can only infer images of 50 keV, if another trained neural network for inferring images of keV other than 50 keV can be prepared, it is expected that this will further contribute to improving diagnostic ability. For example, if a trained neural network for inferring images of keV other than 50 keV is created in addition to the trained neural network for inferring images of 50 keV, it will be possible to infer not only images of 50 keV but also images of keV other than 50 keV, which is expected to greatly contribute to further improving diagnostic ability.

[0035] Therefore, it is conceivable to create a trained neural network for virtual monochromatic X-ray images of each energy and infer virtual monochromatic X-ray images of various energies. For example, if a diagnosis is made using images of 40 keV, 50 keV, 60 keV, 70 keV, 80 keV, 90 keV, 100 keV, 110 keV, 120 keV, 130 keV, and 140 keV as reference, it is possible to infer virtual monochromatic X-ray images of these energies by creating a trained neural network for each of these energies. Therefore, since it is possible to infer virtual monochromatic X-ray images of various energies, it is possible to further improve diagnostic performance.

[0036] However, with the above method, it is necessary to create a trained neural network for each virtual monochromatic X-ray image of each energy. Therefore, it is necessary to prepare training data for each virtual monochromatic X-ray image of the energy to be inferred and train the neural network. This poses the problem of increasing development man-hours.

[0037] Therefore, the inventors of the present invention have conducted extensive research and have devised a method for generating virtual monochromatic X-ray images of various energies without creating a trained neural network for each virtual monochromatic X-ray image of each energy. The basic concept of this method will be explained below with reference to FIG. 2.

[0038] FIG. 2 is a schematic diagram of a curve showing the change in CT number versus energy (keV). FIG. 2 shows curves 11 to 15 obtained for each part of the human body.

[0039] Curve 11 is a curve showing the change in CT value of the kidney with respect to energy (keV), and curve 11 shows the change in CT value when a contrast medium is flowing into the kidney. Curve 12 is a curve showing the change in CT value of bone with respect to energy (keV). Curve 13 is a curve showing the change in CT value of the liver with respect to energy (keV). Curve 14 is a curve showing the change in CT value of a kidney cyst versus energy (keV). Curve 15 is a curve showing the change in CT value of fat with respect to energy (keV).

[0040] These curves 11 to 15 can be created based on data obtained by scanning an actual subject using a CT device equipped with dual-energy technology. Alternatively, a phantom containing common substances found in the human body (e.g., water, iodine, calcium) can be scanned, and CT value curves for each region can be created based on data obtained from the phantom. Alternatively, CT value curves can be created based on both data obtained by scanning the subject and data obtained by scanning the phantom.

[0041] The following will explain how to create curve 12, taking curve 12 as a representative of curves 11 to 15, with reference to FIG.

[0042] To generate the curve 12, first, virtual monochromatic X-ray images are acquired in the energy range of 40 keV to 140 keV based on data obtained by scanning multiple subjects and / or phantoms using dual-energy technology. In this embodiment, virtual monochromatic X-ray images are acquired in increments of 5 keV in the range of 40 keV to 140 keV, but virtual monochromatic X-ray images can be acquired at any keV. For example, virtual monochromatic X-ray images may be acquired in increments of 1 keV or 10 keV. Note that, due to space limitations, only virtual monochromatic X-ray images S1 to Sn acquired by scanning at 40 keV are shown here, but multiple virtual monochromatic X-ray images are also acquired for other energies. Then, from the virtual monochromatic X-ray images acquired in this manner, the CT value of bones is determined for each energy (keV). For example, focusing on 40 keV, the CT value of bones is determined from the virtual monochromatic X-ray images S1 to Sn. In Figure 3, a bar B1 representing the range of CT value variation is shown for 40 keV, and this bar B1 represents the distribution range of CT values ​​for multiple virtual monochromatic X-ray images S1 to Sn. Furthermore, CT values ​​are specified for other energies as well, similar to 40 keV. In Figure 3, bars B2 to B21 representing the range of CT value variation are shown for 45 keV to 140 keV.

[0043] Then, a curve 12 is drawn so as to pass through the range of bars B1 to B21 indicated for each energy (keV). Curve 12 may be drawn so as to pass through the midpoint of the range of CT values ​​defined by each bar, or may be drawn so as to pass through the point where the CT values ​​are most densely concentrated within the range of CT values ​​defined by each bar.

[0044] Although the method for creating the curve 12 has been described with reference to FIG. 3, the other curves 11, 13, 14, and 15 can also be created in a similar manner.

[0045] Therefore, we can see how the CT value changes with energy (keV) from curves 11 to 15. As explained above, a technique has been developed to infer a 50 keV virtual monochromatic X-ray image from a 120 kV CT image.

[0046] The inventors of the present application have conducted extensive research and have found that by utilizing the CT values ​​obtained from the curve and a technique for inferring a 50 keV virtual monochromatic X-ray image from a 120 kV CT image, it is possible to generate a virtual monochromatic X-ray image of an energy other than 50 keV from a single-energy CT image without creating a trained neural network for the virtual monochromatic X-ray image of each energy (keV).The principle of generating a virtual monochromatic X-ray image of an energy other than 50 keV by utilizing the CT values ​​obtained from the curve and a technique for inferring a 50 keV virtual monochromatic X-ray image from a 120 kV CT image will be specifically described below with reference to Figures 4 to 9.

[0047] FIG. 4 is a diagram showing the curve 12. First, determine the energy (keV) of the virtual monochromatic X-ray image corresponding to the tube voltage used in single-energy imaging. Although various voltage values ​​can be used as the tube voltage for single-energy imaging, here we will consider the case where 120 kV is used as the tube voltage for single-energy imaging. In general, the characteristics (e.g., contrast) of a 120 kV CT image can be considered to be sufficiently similar to a 70 keV virtual monochromatic X-ray image. Therefore, the energy of the virtual monochromatic X-ray image corresponding to 120 kV is set to 70 keV.

[0048] Next, a position representing 70 keV is identified on the horizontal axis (keV axis) of the curve 12. In FIG.

[0049] Next, the position of the energy (keV) of the virtual monochromatic X-ray image inferred by the trained neural network is identified from the horizontal axis (keV axis) of curve 12. In this embodiment, the energy of the virtual monochromatic X-ray image inferred by the trained neural network is 50 keV, so the position representing 50 keV is identified on the horizontal axis (keV axis) of curve 12. In Figure 5, the position of 50 keV is indicated by dashed line 22.

[0050] Next, consider the case of generating a virtual monochromatic X-ray image with an energy different from that of the 50 keV virtual monochromatic X-ray image. Here, consider the case of generating a virtual monochromatic X-ray image with an energy of 40 keV. Therefore, the position representing 40 keV on the horizontal axis (keV axis) of curve 12 is identified. In Figure 6, the position of 40 keV is indicated by dashed line 23.

[0051] Next, the relationship between the CT values ​​at 70 keV, 50 keV, and 40 keV will be examined (see FIG. 7).

[0052] FIG. 7 is an explanatory diagram of the relationship between CT values. In Figure 7, the CT value for 70 keV is "v 70 " where v 70 ≒100HU. Also, the CT value of 50keV is "v 50 " where v 50 ≒170HU. Furthermore, the CT value of 40keV is "v 40 " where v 40 ≒240HU. These CT values ​​v 70 , v 50 , and v 40 However, there may be some variation depending on the method for creating the curve 12. For example, the CT value at 70 keV may deviate from 100 HU. However, such deviations in CT values ​​are small enough to be ignored when explaining the effects of this embodiment. Therefore, in the following explanation, the CT value will be described as 100 HU at 70 keV, 170 HU at 50 keV, and 240 HU at 40 keV.

[0053] First, the CT value at 70 keV v 70 and CT value v at 50 keV 50 Calculate the difference ΔCT1 between the two. ΔCT1 is expressed by the following formula. ΔCT1=v 50 -v 70 (1)

[0054] CT value v 70 = 100 HU, and the CT value v 50 = 170HU, ΔCT1 can be calculated using the following formula: ΔCT1=v 50 -v 70 =170HU-100HU =70HU

[0055] Next, the CT value at 70 keV is v 70 and CT value v at 40 keV 40 Calculate the difference ΔCT2 between the two. ΔCT2 can be calculated using the following formula. ΔCT2=v 40 -v 70 (2)

[0056] CT value v 70 = 100 HU, and the CT value v 40 = 240HU, ΔCT2 can be calculated using the following formula: ΔCT2=v 40 -v 70 =240HU-100HU =140HU

[0057] Therefore, ΔCT1 and ΔCT2 can be considered to have the following relationship: ΔCT2=2*ΔCT1 (3)

[0058] From equation (3), we can see that ΔCT2 can be expressed as twice ΔCT1. In other words, if the CT value of 70 keV is used as the reference, the CT value of 40 keV is twice the CT value of 50 keV.

[0059] Next, the relationship between CT values ​​at 70 keV, 50 keV, and 40 keV will be examined for a curve other than curve 12 (see FIG. 8).

[0060] FIG. 8 is an explanatory diagram of the relationship of the CT value of the curve 11. At 70 keV, the CT value is approximately 120 HU, at 50 keV, the CT value is approximately 225 HU, and at 40 keV, the CT value is approximately 330 HU.

[0061] Next, calculate the difference ΔCT1 between the CT value of 120 HU at 70 keV and the CT value of 225 HU at 50 keV. ΔCT1 can be calculated using the following formula. ΔCT1=225HU-120HU =105HU

[0062] Also, calculate the difference ΔCT2 between the CT value of 120 HU at 70 keV and the CT value of 330 HU at 40 keV. ΔCT2 can be calculated using the following formula: ΔCT2=330HU-120HU =210HU

[0063] Therefore, ΔCT1 and ΔCT2 can be considered to have the following relationship: ΔCT2=2*ΔCT1

[0064] Therefore, it can be seen that ΔCT2 can also be expressed as twice ΔCT1 for curve 11. Furthermore, although a detailed explanation will be omitted, ΔCT1 and ΔCT2 for the other CT curves 13 to 15 can also be roughly expressed by the relationship in formula (3).

[0065] From the above considerations, it was found that ΔCT2 can be calculated by multiplying ΔCT1 by the scaling coefficient "2", regardless of the imaging region.

[0066] Furthermore, as shown in equations (1) and (2), ΔCT1 and ΔCT2 are expressed by the following equations. ΔCT1=v 50 -v70 ΔCT2=v 40 -v 70

[0067] Therefore, by substituting these equations (1) and (2) into equation (3), the following equation is obtained: ΔCT2=2*ΔCT1 v 40 -v 70 =2(v 50 -v 70 ) v 40 =2(v 50 -v 70 )+v 70 (4)

[0068] Therefore, the CT value v of a 70 keV virtual monochromatic X-ray image 70 and the CT value v of a 50 keV virtual monochromatic X-ray image 50 It can be seen that the CT value of a 40 keV virtual monochromatic X-ray image can be calculated by substituting into equation (4).

[0069] In addition, in equation (4), the CT value v of a 40 keV virtual monochromatic X-ray image 40 However, the CT values ​​of virtual monochromatic X-ray images of other energies can also be calculated according to the above explanation. For example, a virtual monochromatic X-ray image of 45 keV will be focused on as a virtual monochromatic X-ray image of an energy other than 40 keV, and a case of calculating the CT value of the virtual monochromatic X-ray image of 45 keV will be described. Fig. 9 is an explanatory diagram for calculating the CT value of a virtual monochromatic X-ray image of 45 keV.

[0070] As explained above, the CT value at 70 keV is v 70 is v 70 = 100HU, and the CT value at 50 keV is v 50 is v 50 =170HU. Also, the CT value at 45 keV is v 45 is v 45 =200HU.

[0071] CT value at 70 keV v70 (=100HU) and the CT value v at 50keV 50 The difference ΔCT1 from (=170HU) can be calculated using the following formula. ΔCT1=170HU-100HU =70HU

[0072] Also, the CT value at 70 keV is v 70 (=100HU) and the CT value v at 45keV 45 The difference ΔCT2 from (=200HU) can be calculated using the following formula. ΔCT2=200HU-100HU =100HU

[0073] Therefore, ΔCT1 and ΔCT2 can be considered to have the following relationship: ΔCT2≒1.4*ΔCT1 (5)

[0074] From equation (5), it can be seen that for a 45 keV virtual monochromatic X-ray image, ΔCT2 can be calculated by multiplying ΔCT1 by a scaling factor of 1.4.

[0075] Therefore, the CT value v of a 45 keV virtual monochromatic X-ray image 45 can be calculated by the following formula: v 45 =1.4(v 50 -v 70 )+v 70 (6)

[0076] Therefore, by comparing equations (4) and (6), simply changing the scaling factor in equation (4) from "2" to "1.4" will reduce the CT value v of a 45 keV virtual monochromatic X-ray image. 45 It turns out that it is possible to calculate

[0077] Therefore, in equations (4) and (6), the CT value v 40 and v 45 is defined as "v E" and further substituting the scaling factors "2" and "1.4" for the scaling factor "a", equations (4) and (6) can be generalized to the following equations: v E =a(v 50 -v 70 )+v 70 (7)

[0078] In equation (7), v 70 is the CT value of a 70 keV virtual monochromatic X-ray image, and v 50 is the CT value of the virtual monochromatic X-ray image of 50 keV. Also, a is a scaling coefficient, which defines the relationship between the CT value corresponding to 40 keV and the CT value corresponding to 50 keV, with the CT value corresponding to 70 keV as the reference. Since the scaling coefficient a is a value determined according to the value of energy E, the CT value v of the virtual monochromatic X-ray image of any energy E can be changed simply by changing the value of the scaling coefficient a. E It turns out that it is possible to calculate

[0079] As explained above, the 70 keV virtual monochromatic X-ray image corresponds to the 120 kV CT image. Therefore, the CT value of the 120 kV CT image is expressed by the symbol "v tube_120 ", v in equation (7) 70 is v tube_120 That is, equation (7) can be expressed as follows: v E =a(v 50 -v tube_120 )+v tube_120 (8) where v tube_120 :CT value of 120kV CT image v 50 :CT value of 50keV virtual monochromatic X-ray image v E : CT value of virtual monochromatic X-ray image of energy E

[0080] Therefore, the CT value of a 120 kV CT image is v tube_120and the CT value v of a 50 keV virtual monochromatic X-ray image 50 If we know the CT value v of a virtual monochromatic X-ray image with energy E, E It turns out that can be calculated. In this embodiment, the storage device stores a lookup table that indicates the correspondence between the energy E of a virtual monochromatic X-ray image and the scaling coefficient a (see FIG. 10).

[0081] FIG. 10 is an explanatory diagram of the lookup table LUT1 stored in the storage device. The lookup table LUT1 has a column for the energy E (keV) of the virtual monochromatic X-ray image and a column for the scaling coefficient a. For convenience of explanation, FIG. 10 shows 40 keV, 60 keV, 80 keV, 100 keV, 120 keV, and 140 keV as examples of the energy E (keV). However, the energy E is not limited to these energies, and any energy within the range of 40 keV to 140 keV can be used as an example of the energy E (keV) in the lookup table LUT1. Furthermore, energies smaller than 40 keV and / or larger than 140 keV can also be used as an example of the energy E (keV) in the lookup table LUT1.

[0082] In addition, in the column of scaling coefficient a, the scaling coefficient a corresponding to each energy E is listed as "a 40 "," a 60 "," a 80 "," a 100 "," a 120 ", and "a 140 For example, the scaling factor a for energy E=40 keV is 40 As explained above, 40 = 2. Note that here, the other scaling coefficient "a 60 "," a 80 "," a 100 "," a 120 ", and "a 140Although specific values ​​of " are not shown, the values ​​of these other scaling factors can also be determined in the manner described with reference to FIGS.

[0083] Therefore, the lookup table LUT1 is set to the energy of the virtual monochromatic X-ray image, 40 keV to 140 keV, and the scaling factor a 40 ~a 140 This represents a correspondence relationship between the two. In this embodiment, the formula (8) and the lookup table LUT1 are used to generate a virtual monochromatic X-ray image of an object at any energy. The flow of generating a virtual monochromatic X-ray image of an object at any energy in this embodiment will be described below.

[0084] FIG. 11 is a flow diagram for acquiring a virtual monochromatic X-ray image of an arbitrary energy, and FIGS. 12 to 15 are explanatory diagrams of the steps executed in the flow of FIG.

[0085] In step ST1, the subject is scanned under a scan condition in which a tube voltage of 120 kV is applied to the X-ray tube. The processor reconstructs a CT image of the subject based on data obtained by scanning the subject. FIG. 12 schematically shows a CT image 31 acquired by scanning the subject. After scanning the subject, the process proceeds to step ST2.

[0086] In step ST2, the processor infers a 50 keV virtual monochromatic X-ray image from the CT image 31 using the trained neural network 30. FIG. 13 schematically shows an inferred 50 keV virtual monochromatic X-ray image 32. The processor can infer the 50 keV virtual monochromatic X-ray image 32 by inputting the CT image 31 into the trained neural network 30. The processor may also perform preprocessing on the CT image 31, if necessary, and input the preprocessed CT image 31 into the trained neural network 30 to infer the 50 keV virtual monochromatic X-ray image 32. After inferring the 50 keV virtual monochromatic X-ray image 32, the process proceeds to step ST3.

[0087] In step ST3, the processor generates a virtual monochromatic X-ray image of another energy different from the 50 keV virtual monochromatic X-ray image 32 based on the CT image 31 and the 50 keV virtual monochromatic X-ray image 32. Step ST3 will be described with reference to FIGS. 14 and 15.

[0088] FIG. 14 is an illustration of the equations used to generate virtual monochromatic X-ray images of other energies than the 50 keV virtual monochromatic X-ray image 32. In the following, 40 keV will be considered as an example of another energy, but the same explanation can be applied to energies other than 40 keV.

[0089] First, the processor reads a plurality of scaling coefficients a in a lookup table LUT1 stored in a storage device. 40 ~a 140 The scaling coefficient a corresponding to 40 keV is selected from the above. The scaling coefficient a corresponding to 40 keV is a = a 40 Therefore, the processor obtains the scaling coefficient a=a from the look-up table LUT1. 40 Select the scaling factor a 40 After selecting, the scaling factor a selected for a in Eq. (8) 40 Substitute the following. 40 = 2, so a in equation (8) is a = a 40 = 2 is substituted. Therefore, the following equation is obtained: v E =a(v 50 -v tube_120 )+v tube_120 =2(v 50 -v tube_120 )+v tube_120 (9)

[0090] In addition, since we are considering generating a 40 keV virtual monochromatic X-ray image, v in Eq. (9) E is v 40 Therefore, equation (9) becomes the following equation: v 40 =2(v 50 -v tube_120 )+v tube_120 (10)

[0091] Therefore, the processor calculates the CT value v of the 40 keV virtual monochromatic X-ray image using equation (10). 40 Specifically, the CT value v can be calculated as follows: 40 Calculate.

[0092] Figure 15 shows the CT value v using equation (10). 40 FIG. The processor identifies a pixel Pi of interest from the CT image 31. Then, the CT value v of the pixel Pi of interest is calculated. i Since the CT image 31 is an image obtained with a tube voltage of 120 kV, the processor reads out v tube_120 To, v i Substitute.

[0093] The processor also selects pixel P of the CT image 31 from the 50 keV virtual monochromatic X-ray image 32. i Pixel P at the same position as j CT value v j The CT value v of the 50 keV virtual monochromatic X-ray image 32 is read out. j is the CT value v in equation (10) 50 Since the value represents v in Eq. (10), the processor 50 To, v j Substitute.

[0094] Therefore, the processor calculates the pixel P of the CT image 31 in the 40 keV virtual monochromatic X-ray image 33. i Pixel P at the same position as k CT value v k (=v 40 ) can be calculated. For example, v i = 95HU, and v j = 160HU, v k =225HU.

[0095] In the above description, pixel P of the 40 keV virtual monochromatic X-ray image 33 k CT value v k The procedure for calculating σ has been described above, but calculations can be performed in a similar manner for other pixels of the 40 keV virtual monochromatic X-ray image 33. Therefore, the 40 keV virtual monochromatic X-ray image 33 can be calculated based on the CT image 31 and the 50 keV virtual monochromatic X-ray image 33.

[0096] In the above description, an example has been described in which a 40 keV virtual monochromatic X-ray image 33 is calculated as a virtual monochromatic X-ray image of a different energy from the 50 keV virtual monochromatic X-ray image. However, by using equation (8) and lookup table LUT1, it is possible to calculate virtual monochromatic X-ray images of other energies in addition to the 40 keV virtual monochromatic X-ray image 33. For example, when it is desired to calculate a 60 keV virtual monochromatic X-ray image, the 60 keV virtual monochromatic X-ray image can be calculated based on the following equation:

[0097] v 60 =a 60 (v 50 -v tube_120 )+v tube_120 (11) The above equation (11) is the v E v 60 and the scaling coefficient a in equation (8) is the scaling coefficient a corresponding to the energy of 60 keV. 60 This is the formula obtained by substituting

[0098] The processor calculates v in Eq. (11). tube_120 Substitute the CT value of the CT image 31 into v in equation (11). 50 By substituting the CT value of the 50 keV virtual monochromatic X-ray image 32 into the above, the CT value of the 60 keV virtual monochromatic X-ray image can be calculated.

[0099] Similarly, virtual monochromatic X-ray images of other energies can be calculated. The display device can display not only the 50 keV virtual monochromatic X-ray image 32, but also virtual monochromatic X-ray images of any energy other than 50 keV. Therefore, the user can visually confirm virtual monochromatic X-ray images of various energies. In this way, the flow shown in FIG. 11 ends.

[0100] In the first embodiment, a virtual monochromatic X-ray image of any energy (e.g., 40 keV) desired by the user can be calculated by using a lookup table LUT1 (see FIG. 14 ), which represents the correspondence between energy E (keV) and a scaling coefficient a. Therefore, in the first embodiment, a virtual monochromatic X-ray image of any energy desired by the user can be calculated by using the lookup table LUT1, without creating a trained neural network 30 for virtual monochromatic X-ray images for each energy in the range of 40 keV to 140 keV. Therefore, a virtual monochromatic X-ray image of any energy can be generated without preparing training data for the neural network for each energy in the range of 40 keV to 140 keV or training the neural network for each energy. Therefore, the method of the first embodiment using the lookup table LUT1 can reduce the number of development steps and significantly reduce development costs compared to a method of creating a trained neural network 30 for each energy in the range of 40 keV to 140 keV.

[0101] In this embodiment, the scaling coefficient a is selected from the lookup table LUT1 stored in the storage device. However, instead of storing the lookup table LUT1, a group of CT value data (for example, any one of the curves 11 to 15) that indicates the change in CT value relative to the energy (keV) of the virtual monochromatic X-ray image may be stored, and the scaling coefficient a may be calculated based on the stored group of CT value data.

[0102] In this embodiment, the trained neural network 30 infers a 50 keV virtual monochromatic X-ray image 32 from the CT image 31. However, the inferred virtual monochromatic X-ray image does not necessarily have to be limited to a 50 keV virtual monochromatic X-ray image, and a virtual monochromatic X-ray image of another energy may be inferred instead of the 50 keV virtual monochromatic X-ray image. When the energy of the inferred virtual monochromatic X-ray image is extended to any energy other than 50 keV, Equation (8) can be generalized to the following equation: v E =a(v E_inf -v tube_120 )+v tube_120 (12) Here, v in equation (12) E_inf is the arbitrary energy of the inferred virtual monochromatic X-ray image.

[0103] Therefore, the inferred virtual monochromatic X-ray image is not limited to a virtual monochromatic X-ray image of 50 keV. Even if a virtual monochromatic X-ray image of another energy other than 50 keV is inferred, the CT value v of the virtual monochromatic X-ray image of any energy E E For example, if a trained neural network that infers a 60 keV virtual monochromatic X-ray image from a 120 kV CT image is prepared instead of the trained neural network 30 that infers a 50 keV virtual monochromatic X-ray image from a 120 kV CT image, the CT value v of a virtual monochromatic X-ray image of any energy E desired by the user can be calculated using the 120 kV CT image and the inferred 60 keV virtual monochromatic X-ray image. E In this case, equation (12) can be expressed as follows: v E =a(v E_inf -v tube_120 )+v tube_120 =a(v 60 -v tube_120 )+v tube_120 where v 60 represents the CT value of the inferred 60 keV virtual monochromatic X-ray image.

[0104] In this way, the inferred virtual monochromatic X-ray image is not limited to a virtual monochromatic X-ray image of 50 keV, but a virtual monochromatic X-ray image of any energy other than 50 keV may be inferred.

[0105] In this embodiment, the case where the tube voltage of the X-ray tube is 120 kV has been described. However, the tube voltage of the X-ray tube is not limited to 120 kV, and another tube voltage may be used instead of 120 kV. When the tube voltage of the X-ray tube is expanded to any tube voltage other than 120 kV, Equation (12) can be generalized to the following equation. v E =a(v E_inf -v tube_x )+v tube_x (13) where v tube_x represents the CT value of the CT image obtained when the tube voltage is x (kV).

[0106] Therefore, the tube voltage of the X-ray tube is not limited to 120 kV, and even if the tube voltage is other than 120 kV, the CT value of a virtual monochromatic X-ray image of any energy desired by the user can be calculated.

[0107] In this way, the tube voltage is not limited to 120 kV, and a tube voltage other than 120 kV can also be used.

[0108] (2) Second embodiment The second embodiment will be described in accordance with the flow shown in Fig. 11, similarly to the first embodiment. Note that steps ST1 and ST2 in the second embodiment are the same as steps ST1 and ST2 in the first embodiment. Therefore, steps ST1 and ST2 will be briefly described, and step ST3 will be specifically described.

[0109] First, steps ST1 and ST2 are executed to acquire a CT image 31 and a 50 keV virtual monochromatic X-ray image 32. The CT image 31 and the 50 keV virtual monochromatic X-ray image 32 acquired in steps ST1 and ST2 are shown in Fig. 13. After acquiring the CT image 31 and the 50 keV virtual monochromatic X-ray image 32, the process proceeds to step ST3.

[0110] In step ST3, a 40 keV virtual monochromatic X-ray image is generated based on the CT image 31 and the 50 keV virtual monochromatic X-ray image 32. Note that step ST3 in the second embodiment is different from step ST3 in the first embodiment, and therefore step ST3 in the second embodiment will be described below (see FIG. 16).

[0111] FIG. 16 is a flow diagram of step ST3 in the second embodiment, and FIG. 17 is an explanatory diagram of step ST3.

[0112] In step ST31, the processor generates a difference image 34 between the CT image 31 and the virtual monochromatic X-ray image 32. After generating the difference image 34, the process proceeds to step ST32.

[0113] In step ST32, the processor obtains a scaling factor a corresponding to an energy of 40 keV from the look-up table LUT1. 40 (=2) is read out. Then, the CT value of each pixel in the differential image 34 is calculated by applying a scaling coefficient a 40 = 2 to generate a multiplied image 35. After generating the multiplied image 35, the process proceeds to step ST33.

[0114] In step ST33, the processor adds the multiplied image 35 to the CT image 31. In this way, a 40 keV virtual monochromatic X-ray image 36 can be created.

[0115] In the second embodiment, as in the first embodiment, a virtual monochromatic X-ray image of any energy desired by the user can be calculated by using the lookup table LUT1. Therefore, in the second embodiment, it is not necessary to create a trained neural network 30 for virtual monochromatic X-ray images for each energy (keV), which reduces the number of development steps and significantly reduces development costs.

[0116] (3) Third embodiment In the first and second embodiments, an example in which an object is scanned with the tube voltage of the X-ray tube set to 120 kV has been described. In the third embodiment, an example in which an object is scanned with the tube voltage of the X-ray tube set to a tube voltage different from 120 kV will be described. In the following, 100 kV will be taken as an example of a tube voltage different from 120 kV, and an example in which an object is scanned with the tube voltage of 100 kV will be described, but the tube voltage may be a tube voltage other than 100 kV.

[0117] Before specifically describing the third embodiment, we will first point out the problem that occurs when scanning a subject with a tube voltage (100 kV) different from 120 kV. After clarifying this problem, we will then specifically describe the third embodiment.

[0118] FIG. 18 is an explanatory diagram of the problem that occurs when a subject is scanned at a tube voltage of 100 kV. The 120 kV CT image described in the first and second embodiments corresponds to a 70 keV virtual monochromatic X-ray image (see dashed line 21). On the other hand, a CT image obtained at a tube voltage of 100 kV can generally be considered to correspond to a 64 keV virtual monochromatic X-ray image. In FIG. 18, the position of 64 keV is indicated by dashed line 41. That is, when comparing 100 kV and 120 kV, the energy (keV) is not the same, but there is a deviation of about 6 keV. Therefore, when a CT image (64 keV) obtained at a tube voltage of 100 kV is input to the trained neural network 30, the inferred virtual monochromatic X-ray image is a virtual monochromatic X-ray image of a different energy offset by a certain energy ΔE from 50 keV. In FIG. 18, the energy of the virtual monochromatic X-ray image output by inputting a CT image (64 keV) obtained at a tube voltage of 100 kV to the trained neural network 30 is indicated by dashed line 42. In other words, the energy of the inferred virtual monochromatic X-ray image deviates from 50 keV by ΔE, which causes a problem that a 50 keV virtual monochromatic X-ray image cannot be obtained.

[0119] One possible solution to this problem is to create a new trained neural network 30 that infers a 50 keV virtual monochromatic X-ray image from a 100 kV CT image, separate from the trained neural network 30 that infers a 50 keV virtual monochromatic X-ray image from a 120 kV CT image. However, this method requires preparing not only a trained neural network 30 for 120 kV but also a trained neural network 30 for 100 kV, which increases the development time. Therefore, in the third embodiment, a 50 keV virtual monochromatic X-ray image is generated from a 100 kV CT image without creating a trained neural network 30 for 100 kV. This method is described below.

[0120] FIG. 19 is an explanatory diagram of the principle of generating a 50 keV virtual monochromatic X-ray image from a 100 kV CT image in the third embodiment.

[0121] First, calculate the difference ΔCT3 between the CT value at 50 keV and the CT value at 70 keV. The CT value at 50 keV is 170 HU, and the CT value at 70 keV is 100 HU, so ΔCT3 can be calculated using the following formula. ΔCT3=170HU-100HU =70HU

[0122] Next, calculate the difference ΔCT4 between the CT value at 64 keV and the CT value at 70 keV. The CT value at 64 keV is 115 HU, and the CT value at 70 keV is 100 HU, so ΔCT4 can be calculated using the following formula. ΔCT4=115HU-100HU =15HU

[0123] Therefore, ΔCT3 and ΔCT4 can be considered to have the following relationship: ΔCT4 / ΔCT3=15 / 70

[0124] In this way, the CT value at 64 keV is shifted by ΔCT4 / ΔCT3=15 / 70 relative to the CT value at 70 keV. Therefore, if the CT value vx of the virtual monochromatic X-ray image of the inferred energy Ex is shifted by vx(15 / 70), it can be made to match the CT value of the virtual monochromatic X-ray image of 50 keV (or can be made closer to the CT value of the virtual monochromatic X-ray image of 50 keV).

[0125] Therefore, ΔCT4 / ΔCT3 can be used as the conversion coefficient b for converting the CT value vx of the estimated virtual monochromatic X-ray image of energy Ex into the CT value of a 50 keV virtual monochromatic X-ray image. In the above example, the conversion coefficient b is 15 / 70, but if necessary, the value (15 / 70)w obtained by multiplying 15 / 70 by a weighting coefficient w can also be used as the conversion coefficient b. Note that in the above explanation, curve 12 was used to describe the conversion coefficient b, but the same conversion coefficient b can be obtained even with curves 11 and 13 to 15 for other parts. Therefore, regardless of the imaging part, using the above conversion coefficient b makes it possible to convert the CT value vx of the estimated virtual monochromatic X-ray image into the CT value of a 50 keV virtual monochromatic X-ray image.

[0126] In the above description, a CT image with a tube voltage of 100 kV has been described, but the corresponding conversion coefficient b can also be obtained for other tube voltages according to the above description. In the third embodiment, a lookup table representing the correspondence between the tube voltage x of the X-ray tube and the conversion coefficient b is stored in the storage device (see FIG. 20).

[0127] Fig. 20 is an explanatory diagram of the lookup table LUT2 stored in the storage device. The lookup table LUT2 has a column for the tube voltage x of the X-ray tube and a column for the conversion coefficient b. In Fig. 20, 80 kV, 90 kV, 100 kV, 110 kV, 120 kV, and 130 kV are shown as examples of the tube voltage x, but the energy is not limited to these, and any tube voltage can be used as an example of the tube voltage x in the lookup table LUT2. In addition, in the column of conversion coefficient b, the conversion coefficient b corresponding to each tube voltage is listed as "b 80 "," b 90 "," b 100 "," b 110 "," b 120 " and "b 130 " is indicated.

[0128] Therefore, the lookup table LUT2 is set as follows: tube voltage x = 80 kV to 130 kV and conversion coefficient b = b 80 ~b 130 It represents the correspondence relationship between

[0129] The flow of acquiring a 50 keV virtual monochromatic X-ray image using the lookup table LUT2 in the third embodiment will be described below.

[0130] FIG. 21 is a flow diagram for acquiring a 50 keV virtual monochromatic X-ray image, and FIG. 22 is an explanatory diagram of the flow of FIG.

[0131] In step ST51, the subject is scanned under a scan condition in which a tube voltage of 100 kV is applied to the X-ray tube. The processor reconstructs a CT image of the subject based on data obtained by scanning the subject. FIG. 22 schematically shows a CT image 51 acquired by scanning the subject. After scanning the subject, the process proceeds to step ST52.

[0132] In step ST52, the processor infers a virtual monochromatic X-ray image 52 from a CT image 51 using a trained neural network 30, as shown in FIG. 22 . In the third embodiment, the tube voltage used to acquire the CT image 51 is 100 kV. Meanwhile, the trained neural network 30 is trained to infer a 50 keV virtual monochromatic X-ray image from a 120 kV CT image. Therefore, when a virtual monochromatic X-ray image 52 is inferred from a 100 kV CT image 51 using the trained neural network 30, as described above, the inferred virtual monochromatic X-ray image 52 is not a 50 keV virtual monochromatic X-ray image, but a virtual monochromatic X-ray image 52 of a different energy Ex offset from 50 keV by a certain energy ΔE. Therefore, a 50 keV virtual monochromatic X-ray image cannot be obtained simply by inferring the virtual monochromatic X-ray image 52 from the CT image 51 using the trained neural network 30. Therefore, in the third embodiment, the CT value of the virtual monochromatic X-ray image 52 inferred by the trained neural network 30 is converted into the CT value of a 50 keV virtual monochromatic X-ray image. To perform this conversion, the process proceeds to step ST53. In step ST53, the CT value vx of the virtual monochromatic X-ray image with energy Ex is converted into the CT value v50 of 50 keV using the lookup table LUT2. Step ST53 will be described below. Since step ST53 includes steps ST531 to ST532, each step will be explained in order.

[0133] In step ST531, the processor calculates the conversion coefficient b 80 ~b 130 Select the conversion factor b corresponding to 100kV from the above. 100kV is conversion factor b=b 100 Therefore, the processor calculates the conversion coefficient b corresponding to 100 kV as b=b 100 Select b=b 100 After selecting, the process proceeds to step ST532.

[0134] In step ST532, the processor 100 Based on the above, the CT value vx of the virtual monochromatic X-ray image of energy Ex is converted into the CT value v50 of 50 keV. Specifically, the CT value is converted as follows.

[0135] The processor identifies a pixel Pj of interest from the virtual monochromatic X-ray image 52 of energy Ex (keV), as shown in Fig. 22. Then, the CT value v of the pixel Pj of interest is calculated. j Read out the conversion coefficient b 100 to v j This multiplies the pixel P of the 50 keV virtual monochromatic X-ray image 53. k CT value v k can be calculated.

[0136] In the above explanation, the CT value v of the pixel Pj of the virtual monochromatic X-ray image 52 with energy Ex (keV) j However, other pixels can be converted in a similar manner. Therefore, a 50 keV virtual monochromatic X-ray image 53 can be obtained. In this way, the flow ends.

[0137] In the third embodiment, after a CT image 51 obtained with a tube voltage of 100 kV is obtained, a virtual monochromatic X-ray image 52 is inferred from the CT image 51 using a trained neural network 30. However, the trained neural network 30 is trained to infer a virtual monochromatic X-ray image of 50 keV from a CT image of 120 kV. Therefore, when a CT image 51 obtained with a tube voltage of 100 kV is input to the trained neural network 30, a virtual monochromatic X-ray image 52 offset by a certain energy from 50 keV is output. Therefore, in the third embodiment, in order to obtain a virtual monochromatic X-ray image 53 of 50 keV, the CT value of the virtual monochromatic X-ray image 52 output from the trained neural network 30 is converted to the CT value of the virtual monochromatic X-ray image of 50 keV using a conversion coefficient b. Therefore, in the third embodiment, a 50 keV virtual monochromatic X-ray image 53 can be generated without preparing a new trained neural network for 100 kV in addition to the trained neural network 30 for 120 kV. This eliminates the need to prepare a trained neural network 30 for each X-ray tube voltage, thereby reducing the number of development steps and significantly reducing development costs.

[0138] Furthermore, after generating the 50 keV virtual monochromatic X-ray image 53 in step ST530, a virtual monochromatic X-ray image of another energy other than 50 keV can be calculated using the lookup table LUT1 (see FIG. 14) as in the first embodiment.

[0139] In the third embodiment, the 100 kV CT image 51 is described as an image corresponding to a 64 keV virtual monochromatic X-ray image. However, when an object is irradiated with X-rays, the energy characteristics of the X-rays absorbed by the object vary depending on the size of the object. Therefore, depending on the size of the object, the 100 kV CT image 51 does not necessarily correspond to a 64 keV virtual monochromatic X-ray image. For example, generally, as the object size increases, the energy of the virtual monochromatic X-ray image corresponding to the 100 kV CT image shifts toward higher energy, and as the object size decreases, the energy of the virtual monochromatic X-ray image corresponding to the 100 kV CT image shifts toward lower energy. Therefore, it is desirable to determine the energy (keV) of the virtual monochromatic X-ray image corresponding to the 100 kV CT image based on the size of the object. One example of the size of the object is the diameter of the imaging region. For example, the processor can calculate a water equivalent diameter Dw based on a CT image (e.g., a scout image) of the subject and determine the diameter of the imaging region based on the calculated water equivalent diameter Dw. Therefore, the energy of the virtual monochromatic X-ray image can be determined according to the diameter of the imaging region. Specifically, by storing in the storage device a plurality of diameters of the imaging region (e.g., 20 cm, 25 cm, 30 cm, and 35 cm) and third lookup tables corresponding to each diameter, each of which represents a correspondence relationship between a plurality of tube voltages and a plurality of conversion coefficients b, the third lookup table can be selected according to the determined diameter of the imaging region. Therefore, the conversion coefficient according to the tube voltage can be determined based on the selected third lookup table, thereby further improving the accuracy of the estimated virtual monochromatic X-ray image. [Explanation of symbols]

[0140] 11, 12, 13, 14, 15 curves 21, 22, 23, 41, 42 dashed lines 30 Pre-trained Neural Networks 31, 51 CT images 32, 33, 36, 52, 53 Virtual monochromatic X-ray images 34 Difference Image 35 Multiplication Images 100 CT System 102 Gantry 103 Filter section 104 X-ray tube 105 Precollimator 106 X-ray beam 108 X-ray detector 112 Subject 116 tables 118 Table Motor Controller 202 detector element 210 X-ray controller 212 Gantry motor controller 214 DAS 216 Computer 218 Storage device 220 Operator Console 224 PACS 230 Image Reconstructor 232 Display

Claims

1. 1. A CT system comprising: an X-ray tube to which a tube voltage is applied; one or more processors, reconstructing a first CT image based on data obtained by scanning the subject under a scan condition in which a first tube voltage is applied to the X-ray tube; deducing a virtual monochromatic X-ray image of a second energy different from a first energy corresponding to the first tube voltage based on the first CT image; determining a CT number of the virtual monochromatic X-ray image of the third energy based on a first coefficient that defines a relationship between a second CT number corresponding to the second energy and a third CT number corresponding to a third energy, with reference to a first CT number corresponding to the first energy; one or more processors executing 1. A CT system comprising:

2. the one or more processors: The CT system of claim 1 , wherein a trained neural network is used to infer the second energy virtual monochromatic x-ray image from the first CT image.

3. the one or more processors:

2. The CT system according to claim 1, wherein the CT number of the virtual monochromatic X-ray image of the third energy is determined using a first lookup table representing a correspondence relationship between a plurality of energies of the virtual monochromatic X-ray image and a plurality of first coefficients.

4. the one or more processors: selecting a first coefficient from the plurality of first coefficients of the first lookup table, the first coefficient corresponding to the first energy; generating a virtual monochromatic X-ray image of the third energy based on the selected first coefficients, the first CT image, and the virtual monochromatic X-ray image of the second energy; The CT system of claim 3 , wherein the CT system executes the following:

5. generating the third energy virtual monochromatic X-ray image includes: generating a difference image between the first CT image and the second energy virtual monochromatic X-ray image; multiplying the CT value of the difference image by a first coefficient selected from the plurality of first coefficients to generate a multiplied image; and generating a virtual monochromatic X-ray image of the third energy by adding the multiplied image to the first CT image; The CT system of claim 3 , comprising:

6. the one or more processors: selecting a value of a first coefficient corresponding to the first energy from among the plurality of first coefficients of the first lookup table; multiplying the CT values ​​of the difference image by a selected first coefficient to generate a multiplied image; The CT system of claim 5 , wherein the CT system executes the following:

7. the one or more processors reconstructing a second CT image based on data obtained by scanning the subject under a scan condition in which a second tube voltage is applied to the X-ray tube; inferring a virtual monochromatic X-ray image of another energy different from the second energy from the second CT image using the trained neural network; converting the CT number of the virtual monochromatic X-ray image of the other energy into the CT number of the virtual monochromatic X-ray image of the second energy using a second coefficient; The CT system of claim 2 , wherein the CT system executes the following:

8. the one or more processors 8. The CT system according to claim 7, wherein a second lookup table representing a correspondence relationship between a plurality of tube voltages and a plurality of second coefficients is used to convert the CT numbers of the virtual monochromatic X-ray image of the other energy into the CT numbers of the virtual monochromatic X-ray image of the second energy.

9. the one or more processors: selecting a second coefficient corresponding to the second tube voltage from among the plurality of second coefficients in the second lookup table; 9. The CT system of claim 8, wherein the CT numbers of the virtual monochromatic X-ray image of the other energy are converted to the CT numbers of the virtual monochromatic X-ray image of the second energy based on a selected second coefficient.

10. the one or more processors:

8. The CT system of claim 7, wherein the CT number of the virtual monochromatic X-ray image of the other energy is converted to the CT number of the virtual monochromatic X-ray image of the second energy using the size of the object and a second coefficient.

11. The CT system according to claim 10 , wherein the size of the subject is a diameter of an imaging region of the subject.

12. the one or more processors: The CT system of claim 11 , wherein the diameter of the imaging region is determined based on a scout image of the subject.

13. The storage device includes: Multiple diameters of the imaging area; a third lookup table corresponding to each diameter, the third lookup table representing a correspondence relationship between a plurality of tube voltages and a plurality of second coefficients; is stored, the one or more processors:

13. The CT system according to claim 12, wherein the second coefficient corresponding to the second tube voltage is determined based on a third lookup table corresponding to a diameter of the imaging region determined based on the scout image.

14. the one or more processors:

13. The CT system according to claim 12, wherein a water equivalent diameter is calculated based on a scout image of the subject, and a diameter of the imaging region is determined based on the calculated water equivalent diameter.

15. One or more non-transitory computer-readable storage media having stored thereon instructions that, when executed by the one or more processors, cause the one or more processors to: reconstructing a first CT image based on data obtained by scanning the subject under a scan condition in which a first tube voltage is applied to the X-ray tube; deducing a virtual monochromatic X-ray image of a second energy different from a first energy corresponding to the first tube voltage based on the first CT image; determining a CT number of the virtual monochromatic X-ray image of the third energy based on a first coefficient that defines a relationship between a second CT number corresponding to the second energy and a third CT number corresponding to a third energy, with reference to a first CT number corresponding to the first energy; A storage medium that causes an operation including

Images