Information processing device, learning device, information processing method, and information processing program

Abstract

The present invention provides an information processing device, a learning device, an information processing method, and an information processing program that can provide images that are easy to diagnose. [Solution] An information processing device comprising a processor, the processor acquires multiple imaging data corresponding to radiation with different energies, and generates a color image from the multiple imaging data in which colors are assigned based on an index obtained using the energy information of the radiation.

Description

Technical Field

[0002]

[0001] The present disclosure relates to an information processing apparatus, a learning apparatus, an information processing method, and an information processing program.

Background Art

[0002] In imaging using a CT (Computed Tomography) apparatus, imaging methods such as multi-energy imaging and dual-energy imaging are known. In this imaging method, a plurality of imaging data corresponding to radiation with different energies can be obtained. Techniques for making various images such as reconstructed images generated from the imaging data easy to diagnose are known. For example, Patent Document 1 describes a technique for reducing beam hardening artifacts in multi-energy CT.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the conventional technology, depending on the generated data, there are cases where a huge amount of data has to be diagnosed, and there is room for improvement in order to obtain an image that is easy to diagnose.

[0005] The present disclosure has been made in consideration of the above circumstances, and an object thereof is to provide an information processing apparatus, a learning apparatus, an information processing method, and an information processing program that can provide an image that is easy to diagnose.

Means for Solving the Problems

[0006] To achieve the above objective, an information processing device in a first aspect of the present disclosure includes a processor which acquires a plurality of imaging data corresponding to radiation of different energies and generates a color image from the plurality of imaging data to which colors are assigned based on an index obtained using the energy information of the radiation.

[0007] The second embodiment of the information processing device is an information processing device of the first embodiment in which the index is based on the energy of radiation, the effective energy of radiation, the effective atomic number, the electron density, or characteristic values ​​derived therefrom.

[0008] In the third embodiment of the information processing apparatus, the processor, in the second embodiment of the information processing apparatus, mixes the energy of the corresponding radiation with adjacent imaging data to form a single imaging data and generates a color image.

[0009] In the fourth embodiment of the information processing apparatus, the processor, in the second embodiment of the information processing apparatus, mixes the energy of the corresponding radiation with adjacent imaging data to form a single imaging data, reduces the difference in the number of photons between the imaging data, and generates a color image.

[0010] In the fifth embodiment of the information processing apparatus, if the color image is a color image for identifying a substance having a K absorption edge, the processor mixes adjacent imaging data in the energy direction so as not to cross the K absorption edge.

[0011] The sixth aspect of the information processing apparatus is an information processing apparatus of the first aspect in which the color image is a virtual monochromatic X-ray image.

[0012] The seventh embodiment of the information processing apparatus is an information processing apparatus of the first embodiment in which the color image is a material discrimination image.

[0013] The information processing apparatus of the eighth embodiment is an information processing apparatus of the first embodiment in which the processor reconstructs the captured data to which colors have been assigned, color by color, to generate a reconstructed image.

[0014] The ninth embodiment of the information processing apparatus is an information processing apparatus in the first embodiment in which the processor reconstructs the image data for each radiation energy to generate multiple reconstructed images, generates a difference image of the reconstructed images for each radiation energy, and assigns colors to the difference images to generate a color image.

[0015] In the tenth embodiment of the information processing apparatus, the processor assigns colors according to the energy of the radiation or the interval of the effective energy of the radiation, in the information processing apparatus of the first embodiment.

[0016] In the eleventh embodiment of the information processing apparatus, the processor generates a composite image by combining multiple color images that have different assigned colors, in the information processing apparatus of the first embodiment.

[0017] The twelfth embodiment of the information processing apparatus is an information processing apparatus of the first embodiment in which the processor displays multiple color images, each with a different color, according to window conditions corresponding to each color.

[0018] The 13th embodiment of the information processing device is an information processing device of the first embodiment in which the imaging data is obtained by imaging using a contrast agent, and the processor extracts specific color information corresponding to the contrast agent and outputs a time-dose curve of the contrast agent.

[0019] The 14th embodiment of the information processing device is an information processing device of the first embodiment in which the imaging data is obtained by imaging using a contrast agent, the processor extracts specific color information corresponding to the contrast agent, estimates the time concentration curve of the contrast agent based on the extracted color information, and identifies the start timing of the imaging.

[0020] To achieve the above objective, the learning device of the 15th aspect of the present disclosure generates an image processing model that takes a color image as input and outputs a processed image by training a machine learning model using training data consisting of pairs of color images and correct processed images generated by the information processing device of the present disclosure.

[0021] To achieve the above object, the information processing method according to the 16th aspect of the present disclosure is a method in which a processor acquires a plurality of imaging data corresponding to radiations with different energies, and generates a color image with colors assigned based on an index obtained using the energy information of the radiation from the plurality of imaging data.

[0022] To achieve the above object, the information processing program according to the 17th aspect of the present disclosure is for causing a processor to execute a process of acquiring a plurality of imaging data corresponding to radiations with different energies, and generating a color image with colors assigned based on an index obtained using the energy information of the radiation from the plurality of imaging data.

Advantages of the Invention

[0023] According to the present disclosure, an image that is easy to diagnose can be provided.

Brief Description of the Drawings

[0024] [Figure 1] It is a configuration diagram showing an example of the configuration of the CT apparatus of the embodiment. [Figure 2] It is a configuration diagram showing an example of the configuration of the console of the embodiment. [Figure 3] It is a functional block diagram showing an example of the functions of the console of the embodiment. [Figure 4] It is a flowchart showing an example of the flow of the color image generation process of the embodiment. [Figure 5] It is a diagram for explaining Example 1. [Figure 6] It is a diagram for explaining Example 1. [Figure 7] It is a diagram for explaining Example 1. [Figure 8] It is a diagram for explaining Example 1. [Figure 9] It is a diagram for explaining Example 1. [Figure 10] It is a diagram for explaining Example 2. [Figure 11] It is a diagram for explaining Example 4. [Figure 12A] This is a diagram illustrating Example 5. [Figure 12B] This is a diagram illustrating Example 5. [Modes for carrying out the invention]

[0025] Embodiments of the present invention will be described in detail below with reference to the drawings. Note that these embodiments are not limiting to the present invention.

[0026] First, an example of the configuration of the Computed Tomography (CT) imaging device of this embodiment will be described. Figure 1 shows a configuration diagram representing an example of the configuration of the CT device 10 of this embodiment.

[0027] As shown in Figure 1, the CT apparatus of this embodiment comprises a gantry 20, a patient bed 27, and a console 30. In the following description, the horizontal direction in Figure 1 is referred to as the X-axis, the vertical direction as the Y-axis, and the direction perpendicular to the XY plane as the Z-axis.

[0028] The gantry 20 has an opening 26, and the subject S to be photographed is placed inside the opening 26 while on the bed 27. The gantry 20 and the bed 27 are movable relative to each other in the Z-axis direction.

[0029] Inside the gantry 20, a radiation generator 23 having a radiation tube (not shown), a bowtie filter 24, a collimator 25, and a detector 28 are arranged facing each other with the subject S in between. The radiation R emitted from the radiation generator 23 is shaped into a beam suitable for the size of the subject S by the bowtie filter 24 and collimator 25 and irradiated onto the subject S. The detector 28 detects the radiation that has passed through the subject S and generates projection data corresponding to the dose of the detected radiation.

[0030] The radiation generator 23 and the detector 28 are rotated around the subject S by the rotation drive unit (not shown) of the gantry 20. As radiation irradiation from the radiation generator 23 and detection of radiation by the detector 28 are repeated along with the rotation of both, projection data at various projection angles is acquired. The multiple projection data acquired by the detector 28 are reconstructed by the image reconstruction unit (not shown) of the console 30 and output as an image.

[0031] The CT scanner 10 in this embodiment is a multi-energy CT scanner. A multi-energy CT scanner can acquire multiple projection data corresponding to radiation with different energies. As such a CT scanner 10, for example, the detector 28 outputs projection data corresponding to the photon energy. A photon counting CT scanner equipped with a photon counting type detector may also be used. In addition, any of the following imaging methods may be used: a multi-source / multi-detector method equipped with multiple radiation generators 23 (radiation sources) and multiple detectors 28; a multilayer detector method using a multilayer detector 28 that detects radiation of different energies for each layer; a multi-scan method; an X-ray filter method; and a high-speed tube voltage switching method that changes the energy of the irradiated radiation by switching the tube voltage according to the projection angle.

[0032] The console 30 of this embodiment controls the acquisition of projection data, generates color images, and generates various medical images. The console 30 of this embodiment is an example of an information processing device of the present disclosure. As an example, the console 30 of this embodiment is a server computer.

[0033] As shown in Figure 2, the console 30 comprises a control unit 32, a storage unit 34, an interface unit 35, an operation unit 36, and a display unit 38. The control unit 32, storage unit 34, interface unit 35, operation unit 36, and display unit 38 are connected to each other via a bus 39, such as a system bus or control bus, enabling the exchange of various types of information.

[0034] The control unit 32 in this embodiment controls the overall operation of the console 30. The control unit 32 includes a CPU (Central Processing Unit) 32A, a ROM (Read Only Memory) 32B, and a RAM (Random Access Memory) 32C. The ROM 32B pre-stores various programs, including the information processing program 33 described later, which is executed by the CPU 32A. The RAM 32C temporarily stores various data.

[0035] The memory unit 34 stores projection data output from the detector 28, as well as various other information. Specific examples of the memory unit 34 include storage media such as HDDs (Hard Disk Drives), SSDs (Solid State Drives), and flash memory.

[0036] The I / F unit 35 communicates various types of information with the rotation drive unit (not shown) of the gantry 20, the radiation generator 23, and the detector 28 via wired or wireless communication. In this embodiment, the console 30 receives projection data from the detector 28 via the I / F unit 35. The received projection data is stored in the storage unit 34, associated with the projection angle and the energy of the radiation.

[0037] The operation unit 36 ​​is used by the user to input scan conditions for acquiring projection data, instructions and various information regarding image generation and display, etc. The operation unit 36 ​​is not particularly limited and may include, for example, various switches, buttons, touch panels, styluses, keyboards, and mice. The display unit 38 displays various information, medical images, etc. The operation unit 36 ​​and the display unit 38 may be integrated to form a touch panel display. For example, the operation unit 36 ​​may also accept voice input from the user.

[0038] Figure 3 shows a functional block diagram illustrating an example of the console 30's functions. The console 30 comprises an acquisition unit 40, a color image generation unit 42, and a display control unit 44. As an example, in this embodiment, the CPU 32A of the control unit 32 executes an information processing program 33, causing the CPU 32A to function as the acquisition unit 40, the color image generation unit 42, and the display control unit 44.

[0039] The acquisition unit 40 has the function of acquiring multiple projection data corresponding to radiation with different energies. The acquisition unit 40 may acquire projection data from the detector 28, or, if projection data is stored in the storage unit 34 in advance, it may acquire projection data from the storage unit 34. The acquisition unit 40 outputs the acquired projection data to the color image generation unit 42. The projection data in this embodiment is an example of the imaging data of this disclosure. The imaging data of this disclosure is not limited to projection data, but may also be image data, scan data, etc.

[0040] The color image generation unit 42 has the function of generating a color image from multiple projection data in which colors are assigned based on an index obtained using radiation energy information. The index is based on the radiation energy, the effective energy of the radiation, the effective atomic number, the electron density, or characteristic values ​​derived from these. Which of these the index is used may be specified by the user, or it may depend on the method of imaging, the purpose of imaging or diagnosis, etc.

[0041] Furthermore, the image to be used as a color image, that is, the image to which colors are assigned, may be a reconstructed image or an image obtained by processing projection data, or an image obtained by further processing an image obtained by processing projection data. In addition, the color image generation unit may generate a color image by assigning colors to an image generated from projection data, or it may generate a color image by using projection data to which colors have been assigned.

[0042] The types of colors to be assigned may be predetermined, determined according to indicators, or determined according to user specifications. Furthermore, they may be determined according to the output destination of the color image; for example, when displayed on the display unit 38, RGB-based colors may be used, while when output to a printer or the like to produce printed material, CMYK-based colors may be used.

[0043] The color image generation unit 42 outputs the generated color image to the display control unit 44.

[0044] The display control unit 44 has the function of controlling the display unit 38 to display the color image generated by the color image generation unit 42. If the color image is not to be displayed on the display unit 38, for example, when outputting to an external device, the display control unit 44 outputs image data corresponding to the color image to the output destination.

[0045] Next, the operation of the console 30 in this embodiment will be described.

[0046] In this embodiment, for example, when the console 30 receives a color image output instruction input by the user via the operation unit 36, the CPU 32A of the control unit 32 executes the information processing program 33 stored in the ROM 32B, thereby performing the color image generation process shown as an example in Figure 4. Figure 4 shows a flowchart illustrating an example of the flow of the color image generation process in the console 30 of this embodiment.

[0047] First, in step S100 of Figure 4, the acquisition unit 40 acquires multiple projection data corresponding to radiation with different energies, as described above.

[0048] In the next step S102, the color image generation unit 42 generates a color image, in which colors are assigned based on an index obtained using radiation energy information, from the multiple projection data acquired in step S100, as described above.

[0049] In the next step, S104, the display control unit 44 outputs the color image generated in step S102, as described above. As an example, in this embodiment, it outputs to the display unit 38 and controls the display unit 38 to display the image.

[0050] In color images of each color, there are differences in what is depicted and therefore different contrasts. For this reason, in this embodiment, when displaying color images, the images are displayed with window conditions corresponding to each color, i.e., window conditions corresponding to the contrast. For example, the smaller the contrast, the smaller the window. Specifically, the display control unit 44 sets the window conditions (WW: Window Width, WL: Window Level) independently for each color. In this embodiment, the window width for each color is called the reference window width, and the window level for each color is called the reference window level, and these window conditions are used as the reference window conditions. The window conditions may be transformed using a linear function according to each color. For example, the reference window width may be multiplied by a coefficient, and the reference window level may be added to an offset to set them independently for each color. Furthermore, the method for setting the window conditions may be to maintain preset values ​​in advance according to the combination of base materials, the type of inspection or diagnosis, and the purpose of diagnosis, and allow the user to select or change them. In addition, the energy of the radiation corresponding to the color image and the window width may be linked so that the window width becomes smaller as the energy of the radiation corresponding to the color image increases.

[0051] Once the process in step S104 is completed, the color image generation process shown in Figure 4 is finished.

[0052] Furthermore, specific examples of how to generate color images using console 30 will be described.

[0053] (Example 1) This embodiment describes the case where the CT apparatus 10 is a photon counting CT. As shown in Figure 5, the CT apparatus 10 provides multiple projection data 50e1 to 50e5 for each of the five energy bands (energy bands) of radiation energy (photon energy). The color image generation unit 42 of the console 30 reconstructs the multiple projection data 50e1 for radiation energy e1 to obtain a reconstructed image 60e1, and reconstructs the multiple projection data 50e2 for radiation energy e2 to obtain a reconstructed image 60e2. Furthermore, the color image generation unit 42 reconstructs the multiple projection data 50e3 for radiation energy e3 to obtain a reconstructed image 60e3, reconstructs the multiple projection data 50e4 for radiation energy e4 to obtain a reconstructed image 60e4, and reconstructs the multiple projection data 50e5 for radiation energy e5 to obtain a reconstructed image 60e5. The color image generation unit 42 may assign different colors to each reconstructed image 60e1 to e5 to generate a color image.

[0054] In addition, there are cases where the number of colors to be assigned is fixed, or where there is a bias in the number of photons for each energy band. In such cases, the color image generation unit 42 mixes adjacent projection data 50 for the corresponding radiation energy and generates a color image as a single projection data 50. As an example, as shown in Figure 6, the color image generation unit 42 in this embodiment reconstructs a group of projection data obtained by mixing multiple projection data 50e1 for radiation energy e1 and multiple projection data 50e2 for radiation energy e2 to generate a reconstructed image 60e1e2, and then assigns a color, for example R (red), to the reconstructed image 60e1e2 to generate a color image 70e1e2. Furthermore, the color image generation unit 42 reconstructs multiple projection data 50e3 for radiation energy e3 to generate a reconstructed image 60e3, and then assigns a color, for example G (green), to the reconstructed image 60e3 to generate a color image 70e3. Furthermore, the color image generation unit 42 reconstructs a group of projection data obtained by mixing multiple projection data 50e4 for radiation energy e4 and multiple projection data 50e5 for radiation energy e5 to generate a reconstructed image 60e4e5, and assigns a color, for example B (blue), to the reconstructed image 60e4e5 to generate a color image 70e4e5. Each of the color images 70e1e2, 70e3, and 70e4e5 is an image having a color intensity corresponding to the pixel value.

[0055] The selection of projection data 50 corresponding to each energy may be predetermined or dynamically varied. For example, as shown in Figure 7, the number of photons detected by the detector 28 changes depending on the thickness of the subject S. In the example shown in Figure 7, in case (i), where the thickness of the subject S is average, as described above, the color image generation unit 42 ultimately generates a color image 70e1e2 from a group of projection data obtained by mixing multiple projection data 50e1 and 50e2 corresponding to the respective radiation energies e1 and e2. The color image generation unit 42 also ultimately generates a color image 70e3 from multiple projection data 50e3 for the radiation energy e3. Furthermore, the color image generation unit 42 ultimately generates a color image 70e4e5 from a group of projection data obtained by mixing multiple projection data 50e4 and 50e5 for the respective radiation energies e4 and e5. In case (ii), where the thickness of the subject S is slightly thinner than in case (i), the number of photons detected by the detector 28 decreases according to the thickness. In case (ii), considering the number of photons corresponding to energies e1 to e5, the color image generation unit 42 generates color images 70e1e2, 70e3, and 70e4e5, similar to case (i) above. In case (iii), where the thickness of the subject S is thinner than in case (ii), the number of photons detected by the detector 28 decreases further in proportion to the thickness. In case (iii), considering the number of photons corresponding to energies e1 to e5, the color image generation unit 42 ultimately generates color image 70e1e2e3 from a group of projection data obtained by mixing multiple projection data 50e1 to 50e3 for each of the radiation energies e1 to e3. The color image generation unit 42 also ultimately generates color image 70e4 from multiple projection data 50e4 for the radiation energy e4. The color image generation unit 42 also ultimately generates color image 70e5 from multiple projection data 50e5 for the radiation energy e5.

[0056] In this way, by mixing projection data 50 with adjacent energies such that the difference in the number of photons for each energy (energy band) is reduced, the signal-to-noise ratio of the reconstructed image 60 and the color image 70 can be improved.

[0057] Furthermore, if the color image 70 is a color image for identifying a substance having a K-absorption edge (K-edge), that is, if the substance that the radiologist wants to identify has a K-absorption edge, the color image generation unit 42 may mix adjacent projection data 50 in the energy direction so as not to cross the K-absorption edge. In the example shown in Figure 8, if multiple projection data 50e1 and 50e2 for the radiation energies e1 and e2, respectively, are mixed, it will cross the K-absorption edge. Therefore, in the case shown in Figure 8, the color image generation unit 42 ultimately generates color image 70e1 from multiple projection data 50e1 for the radiation energy e1. Also, it ultimately generates color image 70e2e3 from a group of projection data obtained by mixing multiple projection data 50e2 and 50e3 for the radiation energies e2 and e3, respectively. Furthermore, the color image generation unit 42 ultimately generates color image 70e4e5 from a group of projection data obtained by mixing multiple projection data 50e4 and 50e5 for the radiation energies e4 and e5, respectively.

[0058] In this way, by ensuring that the K absorption edge is not crossed when mixing projection data 50, it is possible to suppress the difficulty in recognizing the effects of the K absorption edge.

[0059] In this embodiment, the CT apparatus 10 may generate a composite image by combining multiple color images 70 that are assigned different colors. For example, as shown in Figure 9, if a color image 70e1e2 is assigned R, a color image 70e3 is assigned G, and a color image 70e4e5 is assigned B, the color image generation unit 42 generates a composite image 80, which is an RGB color image, by combining the color images 70e1e2, 70e3, and 70e4e5. With the composite image 80, which is a color image formed by combining each color image 70, it becomes easier to identify substances according to the differences in color.

[0060] Thus, according to the console 30 of this embodiment, it is possible to provide images that are easy to diagnose.

[0061] (Example 2) In Example 1, the case where the CT device 10 is a photon counting CT was described. In this example, the case where the CT device 10 performs multi-energy imaging by varying the energy of the radiation reaching the detector 28 is described.

[0062] As shown in Figure 10, with the CT scanner 10, multiple projection data 50_80 are obtained by imaging with a tube voltage of 80kV. The color image generation unit 42 of the console 30 reconstructs the multiple projection data 50_80 to obtain a reconstructed image 60_80, and by assigning a color (e.g., R) to the reconstructed image 60_80, a color image 70_80 is generated. In addition, multiple projection data 50_110 are obtained by imaging with a tube voltage of 110kV. The color image generation unit 42 of the console 30 reconstructs the multiple projection data 50_110 to obtain a reconstructed image 60_110, and by assigning a color (e.g., G) to the reconstructed image 60_110, a color image 70_110 is generated. In addition, multiple projection data 50_140 are obtained by imaging with a tube voltage of 140kV. The color image generation unit 42 of the console 30 reconstructs multiple projection data 50_140 to obtain a reconstructed image 60_140, and generates a color image 70_140 by assigning a color (for example, B) to the reconstructed image 60_140.

[0063] Thus, in the console 30 of this embodiment, a color image 70 can be generated in the same way as in the first embodiment. Therefore, in the console 30 of this embodiment, an image that is easy to diagnose can also be provided.

[0064] (Example 3) The color image 70 may be a virtual monochromatic X-ray image, and the colors assigned may differ depending on the energy of the radiation. For example, a color image 70 that is a virtual monochromatic X-ray image may be generated from projection data 50 corresponding to an energy of 40 keV, a color image 70 that is a virtual monochromatic X-ray image may be generated from projection data 50 corresponding to an energy of 70 keV, and a color image 70 that is a virtual monochromatic X-ray image may be generated from projection data 50 corresponding to an energy of 100 keV. By combining these three types of color images 70 with different assigned colors, the visibility of the combined image 80 can be improved. In this case, the user may be allowed to specify the energy to which the colors are assigned.

[0065] Furthermore, the color image 70 may also be a substance discrimination image, and the colors assigned to it may differ depending on the reference substance. For example, if the reference substances are water, bone, and iodine (contrast agent), a color image 70 that is a substance discrimination image for water may be generated, a color image 70 that is a substance discrimination image for bone may be generated, and a color image 70 that is a substance discrimination image for iodine may be generated. By combining these three types of color images 70 with different assigned colors, the visibility of the combined image 80 can be improved. In this case, the user may be allowed to specify the reference substance to which the color is assigned.

[0066] Thus, even in the console 30 of this embodiment, it is possible to provide images that are easy to diagnose.

[0067] (Example 4) The console 30 may generate difference images of the reconstructed image 60 for each radiation energy and assign colors to the difference images to generate a color image 70. In the example shown in Figure 11, the color image generation unit 42 generates difference images 65_80, 65_110, and 65_140 for each of the reconstructed images 60_80, 60_110, and 60_140 described in Example 2. Difference image 65_80 is the difference image between the reference image 62 and the reconstructed image 60_80. Difference image 65_110 is the difference image between the reference image 62 and the reconstructed image 60_110. Difference image 65_140 is the difference image between the reference image 62 and the reconstructed image 60_140. Note that the reference image 62 may be an image obtained by performing a predetermined process on the reconstructed images 60_80, 60_110, and 60_140. Examples of images in this case include images obtained by averaging the pixel values ​​of each reconstructed image 60. Furthermore, the reference image 62 may be any of the reconstructed images 60_80, 60_110, or 60_140, and the reference image 62 may differ depending on which of the reconstructed images 60_80, 60_110, or 60_140 is being used for difference calculation.

[0068] The color image generation unit 42 assigns different colors to each of the difference images 65_80, 65_110, and 65_140 to generate color images 70_80, 70_110, and 70_140. By combining the color images 70_80, 70_110, and 70_140, the visibility of the composite image 80 can be improved.

[0069] Thus, even in the console 30 of this embodiment, it is possible to provide images that are easy to diagnose.

[0070] (Example 5) The color image generation unit 42 of the console 30 may generate a color image 70 by assigning colors corresponding to the energy of the radiation or the intervals of the effective energy of the radiation. Figure 12 shows a method by which the color image generation unit 42 identifies colors corresponding to the energy intervals of the radiation. In the example shown in Figure 12A, an example is shown in which the energy of the radiation is associated with the color wheel 90. The color image generation unit 42 associates a reference energy with a reference color in the color wheel 90. The color image generation unit 42 assigns a color to the desired energy of the radiation by associating the energy interval with the color wheel 90.

[0071] As shown in Figure 12B, the color image generation unit 42 may assign colors to reference substances (water, iodine, and calcium in Figure 12B) based on the color wheel 90, etc. By assigning colors in this way, colors can be assigned according to the characteristics of the image. The color image generation unit 42 may also assign colors in correspondence with the color wheel 90 based on the effective atomic number.

[0072] (Example 6) In this embodiment, we will describe the case where the projection data 50 of the CT apparatus 10 is obtained by imaging using a contrast agent.

[0073] The color image generation unit 42 of the console 30 generates a color image 70 by assigning a color to each radiation energy (Bin) of the reconstructed image 60. Let's explain the case where red is assigned to the first Bin with the lowest photon energy, green to the second Bin with intermediate energy, and blue to the third Bin with the highest photon energy. When the contrast agent is iodine, the CT value increases as the energy decreases. Therefore, it will appear reddish. This is similar to the behavior of calcium. Also, when the contrast agent is gadolinium, the CT value at the second Bin increases. Therefore, it will appear greenish. This makes it easier to distinguish between gadolinium and iodine. Also, when it is acrylic, the CT value increases as the energy increases. Therefore, it will appear bluish. This is similar to the behavior of fat. Also, when it is water, it shows a constant CT value regardless of energy. Therefore, it will appear grayish (black and white).

[0074] As the colors appear differently depending on the contrast agent and tissue, the console 30 can obtain various information by extracting specific color information. For example, the console 30 may extract specific color information corresponding to the contrast agent and generate a time-concentration curve of the contrast agent.

[0075] Alternatively, for example, console 30 may extract specific color information corresponding to the contrast agent, estimate the time-to-time concentration curve of the contrast agent, and determine the start timing of the main contrast imaging based on the estimation results. Specifically, during bolus tracking, specific color information corresponding to the contrast agent may be extracted, and the timing when the contrast agent concentration reaches a desirable state may be identified as the start timing of the main imaging.

[0076] Furthermore, the embodiment of this example is more effective when applied to bolus tracking of two types of contrast agents, gadolinium and iodine.

[0077] (Example 7) Console 30 may generate an image processing model that takes the color image 70 as input and outputs a processed image by training a machine learning model using training data consisting of pairs of the generated color image 70 and the correct processed image. Examples of processed images in this case include denoised images, segmented images, and artifact-removed images. In order to achieve high accuracy in learning, it is preferable that the training data corresponding to the input color data is also color data. Furthermore, it is preferable that the information content corresponding to the hue of the input data (e.g., energy (keV), effective atomic number, and reference material) matches the information content corresponding to the hue of the training data. It is also preferable to match the number of colors in the color data with the number of colors during learning by modifying at least one of the network's internal parameters (e.g., the activation function parameter) according to the number of colors, or by setting an unused color to a value of zero. In this way, by modifying the activation function parameter according to the number of colors, it is possible to prevent incorrect results by reducing the output of the activation function corresponding to the uninputted color. The network may be switched according to the number of colors in the color image 70. Console 30 in this embodiment is an example of the learning device of this disclosure.

[0078] According to this embodiment, it is possible to generate an image processing model that can output highly accurate processed images.

[0079] As described above, the console 30 of each of the above embodiments can provide images that are easy to diagnose.

[0080] Furthermore, in this embodiment, each process is executed on any computer. Alternatively, any computer may execute these processes using a processor as hardware, a program as software, or a combination thereof. In that case, the processor is configured to work in cooperation with the program to execute the various processes in this embodiment, and can function as a unit or means in this embodiment. The execution order of the processes by the processor is not limited to the order described and may be changed as appropriate. Any computer may be a general-purpose computer, a computer designed for a specific purpose, a workstation, or any other system capable of executing each process.

[0081] A processor may consist of one or more hardware components, and the type of hardware is not limited. For example, a processor may consist of a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a programmable logic device such as an FPGA (Field Programmable Gate Array), a dedicated circuit for executing a specific process such as an ASIC (Application Specific Integrated Circuit), a GPU (Graphic Processing Unit), or an NPU (Neural Processing Unit). Furthermore, the type of hardware may be a combination of different types of hardware. When multiple hardware components are configured to execute one or more processes of a processor, these components may reside in physically separate devices or in the same device. Also, in any embodiment, the order of each process performed by the processor is not limited to the order described above and may be changed as appropriate. Hardware is composed of electrical circuits (circuitry) that combine circuit elements such as semiconductor elements.

[0082] Furthermore, the program may be firmware or software such as microcode. Alternatively, the program may be, for example, a set of program modules, each function of which may be implemented by a processor configured to perform its respective function. The program may be program code or multiple code segments stored on one or more non-temporary computer-readable media (e.g., storage media or other storage). The program may be divided and stored on multiple non-temporary computer-readable media located on physically separate devices. Program code or code segments may represent any combination of procedures, functions, subprograms, routines, subroutines, modules, software packages, classes, or instructions, data structures, or program statements. Program code or code segments may be connected to other code segments or hardware circuits by sending and receiving information, data, arguments, parameters, or memory contents.

[0083] Furthermore, although the above embodiment describes an embodiment in which the information processing program 33 is pre-stored (installed) in the ROM 32B, the invention is not limited to this. The information processing program 33 may be provided in the form of a recording medium such as a CD-ROM (Compact Disc Read Only Memory), DVD-ROM (Digital Versatile Disc Read Only Memory), or USB (Universal Serial Bus) memory. Alternatively, the information processing program 33 may be provided in the form of a download from an external device via a network.

[0084] Furthermore, the technology disclosed herein extends to all program products. Program products include all forms of products for providing programs. For example, program products include programs provided via networks such as the Internet, and non-temporary computer-readable recording media such as CD-ROMs, DVDs, and USB memory sticks on which programs are stored.

[0085] Furthermore, the configuration and operation of the CT apparatus 10, console 30, etc., described in each of the above embodiments are merely examples and can be modified as needed without departing from the spirit of the present invention. It also goes without saying that the above embodiments may be combined as appropriate.

[0086] Furthermore, the present invention can also be applied to programs and program products.

[0087] The following additional information is disclosed regarding the above-described embodiments. (Note 1) Equipped with a processor, The aforementioned processor, By acquiring multiple imaging data corresponding to radiation with different energies, A color image is generated from the multiple imaging data, in which colors are assigned based on an index obtained using the energy information of the aforementioned radiation. Information processing device.

[0088] (Note 2) The aforementioned index is based on the energy of the radiation, the effective energy of the radiation, the effective atomic number, the electron density, or characteristic values ​​derived therefrom. The information processing device described in Appendix 1.

[0089] (Note 3) The processor mixes the energy of the corresponding radiation with adjacent imaging data to form a single imaging data, and generates the color image. The information processing device described in Appendix 1 or Appendix 2.

[0090] (Note 4) The processor mixes the energy of the corresponding radiation with adjacent imaging data to create a single imaging data, reduces the difference in the number of photons between the imaging data, and generates the color image. The information processing device described in Appendix 1 or Appendix 2.

[0091] (Note 5) If the aforementioned color image is a color image for identifying a substance having a K absorption edge, The aforementioned processor, The imaging data adjacent to the K absorption edge in the energy direction are mixed so as not to cross the aforementioned K absorption edge. The information processing device described in Appendix 3 or Appendix 4.

[0092] (Note 6) The aforementioned color image is a virtual monochromatic X-ray image. An information processing device as described in any one of the appendices 1 through 5.

[0093] (Note 7) The aforementioned color image is a material discrimination image. An information processing device as described in any one of the appendices 1 through 5.

[0094] (Note 8) The aforementioned processor, The captured data, to which colors have been assigned, is reconstructed for each color to generate a reconstructed image.

[0095] An information processing device as described in any one of the appendices 1 through 5.

[0096] (Note 9) The aforementioned processor, The imaging data is reconstructed for each energy of the aforementioned radiation to generate multiple reconstructed images. A difference image of the reconstructed image is generated for each energy of the aforementioned radiation. The color image is generated by assigning colors to the difference image. An information processing device as described in any one of the appendices 1 through 5.

[0097] (Note 10) The aforementioned processor, The colors are assigned according to the energy of the radiation or the interval of the effective energy of the radiation. An information processing device as described in any one of the appendices 1 through 9.

[0098] (Note 11) The aforementioned processor, Generates a composite image by combining multiple color images with different assigned colors. An information processing device as described in any one of the appendices 1 through 10.

[0099] (Note 12) The aforementioned processor, Multiple color images, each with a different color, are displayed according to window conditions corresponding to each color. An information processing device as described in any one of the appendices 1 through 11.

[0100] (Note 13) The aforementioned imaging data was obtained by imaging using a contrast agent. The aforementioned processor, Extract specific color information corresponding to the aforementioned contrast agent, Output the time-concentration curve of the contrast agent. The information processing device described in Appendix 1.

[0101] (Note 14) The aforementioned imaging data was obtained by imaging using a contrast agent. The aforementioned processor, Extract specific color information corresponding to the aforementioned contrast agent, Based on the extracted color information, the time-concentration curve of the contrast agent is estimated. Determine the start time for the main shoot. The information processing device described in Appendix 1.

[0102] (Note 15) By training a machine learning model using training data consisting of pairs of color images generated by an information processing device described in any one of Appendix 1 to Appendix 14 and correct processed images, an image processing model is generated that takes the color images as input and outputs processed images. Learning device.

[0103] (Note 16) The processor, By acquiring multiple imaging data corresponding to radiation with different energies, A color image is generated from the multiple imaging data, in which colors are assigned based on an index obtained using the energy information of the aforementioned radiation. Information processing methods.

[0104] (Note 17) In the processor, By acquiring multiple imaging data corresponding to radiation with different energies, A color image is generated from the multiple imaging data, in which colors are assigned based on an index obtained using the energy information of the aforementioned radiation. An information processing program used to execute a process. [Explanation of Symbols]

[0105] 10 CT device 20 Gantry 23 Radiation Generator 24 Bowtie Filters 25 Collimator 26 Opening 27 berths 28 detectors 30 Console 32 control unit, 32A CPU, 32B ROM, 32C RAM 33 Information Processing Programs 34 Storage section 35 I / F section 36 Operation section 38 Display section 39 bus 40 Acquisition Department 42 Color Image Generation Unit 44 Display Control Unit Projection data for 50e1~50e5, 50_80, 50_110, and 50_140. 60e1~60e5, 60e1e2, 60e4e5, 60_80, 60_110, 60_140 Reconstructed image 62 Reference Images 65_80, 65_110, 65_140 difference images 70e3~70e5, 70e1e2, 70e1e2e3, 70e2e3, 70e4e5, 70_80, 70_110, 70_140 Color Images e1~e5 Energy (Energy Band) 80 Composite Images 90 Hue wheel R radiation S subject

Claims

1. Equipped with a processor, The aforementioned processor, By acquiring multiple imaging data corresponding to radiation with different energies, A color image is generated from the multiple imaging data, in which colors are assigned based on an index obtained using the energy information of the aforementioned radiation. Information processing device.

2. The aforementioned index is based on the energy of the radiation, the effective energy of the radiation, the effective atomic number, the electron density, or characteristic values ​​derived therefrom. The information processing apparatus according to claim 1.

3. The processor mixes the energy of the corresponding radiation with adjacent imaging data to form a single imaging data, and generates the color image. The information processing apparatus according to claim 2.

4. The processor mixes the energy of the corresponding radiation from adjacent imaging data into a single imaging data, reduces the difference in the number of photons between the imaging data, and generates the color image. The information processing apparatus according to claim 2.

5. If the aforementioned color image is a color image for identifying a substance having a K absorption edge, The aforementioned processor, The imaging data adjacent to the K absorption edge in the energy direction are mixed so as not to cross the aforementioned K absorption edge. The information processing apparatus according to claim 3.

6. The aforementioned color image is a virtual monochromatic X-ray image. The information processing apparatus according to claim 1.

7. The aforementioned color image is a material discrimination image. The information processing apparatus according to claim 1.

8. The aforementioned processor, The captured data, to which colors have been assigned, is reconstructed for each color to generate a reconstructed image. The information processing apparatus according to claim 1.

9. The aforementioned processor, The imaging data is reconstructed for each energy of the aforementioned radiation to generate multiple reconstructed images. A difference image of the reconstructed image is generated for each energy of the aforementioned radiation. The color image is generated by assigning colors to the difference image. The information processing apparatus according to claim 1.

10. The aforementioned processor, The colors are assigned according to the energy of the radiation or the interval of the effective energy of the radiation. The information processing apparatus according to claim 1.

11. The aforementioned processor, Generates a composite image by combining multiple color images with different assigned colors. The information processing apparatus according to claim 1.

12. The aforementioned processor, Multiple color images, each with a different color, are displayed according to window conditions corresponding to each color. The information processing apparatus according to claim 1.

13. The aforementioned imaging data was obtained by imaging using a contrast agent. The aforementioned processor, Extract specific color information corresponding to the aforementioned contrast agent, Output the time-concentration curve of the contrast agent. The information processing apparatus according to claim 1.

14. The aforementioned imaging data was obtained by imaging using a contrast agent. The aforementioned processor, Extract specific color information corresponding to the aforementioned contrast agent, Based on the extracted color information, the time-concentration curve of the contrast agent is estimated. Determine the start time for the main shoot. The information processing apparatus according to claim 1.

15. By training a machine learning model using training data consisting of a pair of a color image generated by the information processing device described in any one of claims 1 to 14 and a correct processed image, an image processing model is generated that takes the color image as input and outputs a processed image. Learning device.

16. The processor, By acquiring multiple imaging data corresponding to radiation with different energies, A color image is generated from the multiple imaging data, in which colors are assigned based on an index obtained using the energy information of the aforementioned radiation. Information processing methods.

17. In the processor, By acquiring multiple imaging data corresponding to radiation with different energies, A color image is generated from the multiple imaging data, in which colors are assigned based on an index obtained using the energy information of the aforementioned radiation. An information processing program used to execute a process.

Images