X-ray imaging system and image processing method

Abstract

This X-ray imaging system (100) comprises an image processing unit (9) that generates, on the basis of a plurality of X-ray images (10), a bone suppression tomographic image (20), which is a tomographic image showing a cross-section of a subject (101) in which a bone structure is suppressed at a target site. The image processing unit (9) includes: a bone suppression processing unit (92) that executes a process to suppress the bone structure at the target site; a reconstruction processing unit (93) that executes a reconstruction process for generating the tomographic image; and an adjustment processing unit (94) that adjusts the degree of suppression of the bone structure in the generated bone suppression tomographic image (20).

Description

[Technical Field]

[0001] The present invention relates to an X-ray imaging system and an image processing method. [Background technology]

[0002] A tomographic image generating system for performing tomosynthesis imaging has been known in the past. Such a system is disclosed, for example, in Japanese Patent Application Laid-Open No. 2016-22095.

[0003] The tomographic image generating system described in JP 2016-22095 A includes a radiation imaging device and a console. The radiation imaging device includes a radiation source that irradiates radiation and a radiation detector that detects the radiation. The radiation imaging device is configured to perform tomosynthesis imaging multiple times while the radiation source and the radiation detector move synchronously, and to acquire a projection image for each imaging. The console then reconstructs the projection images acquired by the radiation imaging device to generate a reconstructed image of the subject. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2016-22095 Summary of the Invention [Problem to be solved by the invention]

[0005] Although not described in the above-mentioned JP 2016-22095 A, tomosynthesis imaging has a limited irradiation angle range for acquiring images compared to CT imaging, which may result in false images (artifacts) of bones (bone structures) appearing in the generated reconstructed images (tomographic images). For example, when generating a tomographic image of a cross section of the lung, false images of ribs may appear in the cross-sectional portion of the lung. In this case, the false images of the ribs reduce the visibility of lesions in the lung. As such, there is a problem in that the visibility of target regions inside the subject's body is reduced due to bone artifacts appearing in areas where no bones actually exist in the generated tomographic image.

[0006] The present invention has been made to solve the above-mentioned problems, and one object of the present invention is to provide an X-ray imaging system and an image processing method that can suppress a decrease in visibility of a target area caused by bone artifacts when generating a tomographic image showing a cross-section of a subject. [Means for solving the problem]

[0007] In order to achieve the above object, an X-ray imaging system according to a first aspect of the present invention includes an X-ray irradiator that irradiates a target region of a subject with X-rays; an X-ray detector that detects the X-rays irradiated from the X-ray irradiator; a movement mechanism that moves at least one of the X-ray irradiator and the X-ray detector; an imaging controller that performs tomosynthesis imaging of the target region of the subject while moving at least one of the X-ray irradiator and the X-ray detector by the movement mechanism; and an image processor that generates, based on a plurality of X-ray images generated by performing tomosynthesis imaging, bone-suppressed tomographic images that are tomographic images showing a cross section of the subject in which bone structures in the target region are suppressed, and based on the plurality of generated X-ray images, the image processor Using a trained model trained using training input images containing bone structures and training output images in which bone structures have been suppressed or removed from the training input images, The system includes a bone suppression processing unit that performs processing to suppress bone structures in the target area, a reconstruction processing unit that performs reconstruction processing to generate a tomographic image based on the multiple X-ray images generated, and an adjustment processing unit that adjusts the degree of suppression of bone structures in the generated bone-suppressed tomographic image.

[0008] An image processing method according to a second aspect of the present invention includes the steps of: generating a plurality of X-ray images by performing tomosynthesis imaging on a target region of a subject while moving at least one of an X-ray irradiation unit that irradiates X-rays onto the target region of a subject and an X-ray detection unit that detects the X-rays irradiated from the X-ray irradiation unit; and generating, based on the plurality of X-ray images generated by performing tomosynthesis imaging, a bone-suppressed tomographic image that is a tomographic image showing a cross section of the subject in which bone structures in the target region are suppressed, wherein the step of generating the bone-suppressed tomographic image includes the steps of: Using a trained model trained using training input images containing bone structures and training output images in which bone structures have been suppressed or removed from the training input images, The method includes the steps of: performing a process to suppress bone structures in the target area; performing a reconstruction process to generate a tomographic image based on the generated multiple X-ray images; and adjusting the degree of suppression of bone structures in the generated bone-suppressed tomographic image. [Effects of the Invention]

[0009] The X-ray imaging system according to the first aspect and the image processing method according to the second aspect generate bone-suppressed tomographic images, which are tomographic images showing a cross section of a subject in which bone structures in the target region are suppressed. By performing a process for suppressing bone structures (bone suppression process), bone structures (artifacts) can be suppressed in the tomographic images. Therefore, bone structures can be prevented from appearing in areas of the generated tomographic images where no bones actually exist. As a result, when generating tomographic images showing a cross section of the subject, a decrease in visibility of the target region due to bone artifacts can be suppressed. Furthermore, by adjusting the degree of bone structure suppression in the generated bone-suppressed tomographic images, adjustments can be made to more accurately suppress bone structures when the degree of bone structure suppression is excessive or insufficient. As a result, a decrease in visibility of the target region can be further suppressed in the generated bone-suppressed tomographic images. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram for explaining the configuration of an X-ray imaging system according to a first embodiment. [Figure 2] FIG. 1 is a block diagram for explaining the configuration of an X-ray imaging system according to a first embodiment. [Figure 3] FIG. 2 is a diagram for explaining generation of a bone-suppressed tomographic image according to the first embodiment. [Figure 4] FIG. 2 is a diagram showing a display on a display unit according to the first embodiment. [Figure 5] FIG. 2 is a diagram for explaining tomosynthesis imaging according to the first embodiment. [Figure 6] FIG. 4 is a diagram for explaining image processing for suppressing bone structures according to the first embodiment. [Figure 7] FIG. 3 is a diagram for explaining a reconstruction process according to the first embodiment. [Figure 8] 5A to 5C are diagrams for explaining adjustment of the degree of suppression of bone structures in bone-suppressed tomographic images according to the first embodiment. [Figure 9] FIG. 3 is a diagram for explaining an adjustment region in the first embodiment. [Figure 10] FIG. 2 is a flowchart illustrating an image processing method according to the first embodiment. [Figure 11] FIG. 10 is a block diagram for explaining the configuration of an X-ray imaging system according to a second embodiment. [Figure 12] 10A and 10B are diagrams for explaining adjustment of the degree of suppression of bone structures in bone-suppressed tomographic images according to the second embodiment. [Figure 13] FIG. 10 is a diagram for explaining the configuration of an X-ray imaging system according to a third embodiment. [Figure 14] 10A and 10B are diagrams for explaining adjustment of the degree of suppression of bone structures in bone-suppressed tomographic images according to the third embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0011] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, specific embodiments of the present invention will be described with reference to the accompanying drawings.

[0012] [First embodiment] (Overall configuration of X-ray imaging system) An X-ray imaging system 100 according to a first embodiment of the present invention will be described with reference to FIGS.

[0013] As shown in FIG. 1, an X-ray imaging system 100 performs X-ray imaging (tomosynthesis imaging) of a target region of a subject 101 to generate a tomographic image showing a cross section of the subject 101. In the first embodiment, the target region of the subject 101 is the thorax and abdomen (chest and abdomen). The X-ray imaging system 100 performs tomosynthesis imaging of the thorax and abdomen of the subject 101 to generate a tomographic image for examining the lungs of the subject 101. The X-ray imaging system 100 generates a bone-suppressed tomographic image 20 (see FIG. 3), which is a tomographic image in which bone structures in the thorax and abdomen of the subject 101 are suppressed, and is configured to be able to adjust the degree of suppression of the bone structures in the generated bone-suppressed tomographic image 20.

[0014] 2, the X-ray imaging system 100 includes an X-ray imaging device 100a and an image processing device 100b. The X-ray imaging device 100a includes a tabletop 1, an X-ray irradiation unit 2, an X-ray detection unit 3, a movement mechanism 4, and an imaging control unit 5. The image processing device 100b includes an operation unit 6, a display unit 7, a storage unit 8, and an image processing unit 9. The image processing device 100b is, for example, a PC (personal computer) used by an operator such as a doctor.

[0015] <Parts of the X-ray device> The tabletop 1 is a bed on which the subject 101 lies. The X-ray irradiator 2 irradiates X-rays onto the chest and abdomen of the subject 101 lying on the tabletop 1. The X-ray irradiator 2 includes an X-ray tube that irradiates X-rays when a voltage is applied. The X-ray detector 3 detects the X-rays irradiated from the X-ray irradiator 2 and transmitted through the subject 101. The X-ray detector 3 includes, for example, an FPD (Flat Panel Detector). The X-ray detector 3 is configured to be able to communicate with the image processor 9 (described later) via a wireless connection such as a wireless LAN, and outputs a detection signal (image signal) as a wireless signal to the image processor 9 based on the detected X-rays.

[0016] As shown in FIG. 1, the movement mechanism 4 moves at least one of the X-ray irradiator 2 and the X-ray detector 3 based on a signal from the imaging controller 5. Specifically, the movement mechanism 4 changes the relative positions of the X-ray irradiator 2 and the X-ray detector 3 by moving both the X-ray irradiator 2 and the X-ray detector 3. The movement mechanism 4 includes an irradiation unit holder 4a, an irradiation unit mover 4b, and a detector mover 4c. The irradiation unit holder 4a rotatably holds the X-ray irradiator 2. That is, the irradiation unit holder 4a is configured to change the irradiation angle of the X-ray irradiator 2 based on a signal from the imaging controller 5. The irradiation unit mover 4b moves the irradiation unit holder 4a in the X direction in FIG. 1. The detector mover 4c moves the X-ray detector 3 in the X direction, which is opposite to the direction in which the X-ray irradiator 2 moves.

[0017] The imaging control unit 5 controls the X-ray imaging by controlling the X-ray irradiator 2 and the X-ray detector 3. Specifically, the imaging control unit 5 is configured to perform X-ray imaging (tomosynthesis imaging) to generate multiple X-ray images 10 (see FIG. 3) of the chest and abdomen of the subject 101 while controlling the moving mechanism 4 to move the X-ray irradiator 2 and the X-ray detector 3. The imaging control unit 5 includes a processor such as a CPU (Central Processing Unit) or an FPGA (Field-Programmable Gate Array). The X-ray images 10 are an example of "images before bone suppression" in the claims.

[0018] <Parts of the image processing device> The operation unit 6 receives an input operation from an operator such as a doctor. The operation unit 6 includes, for example, a keyboard and a pointing device such as a mouse. In the first embodiment, the operation unit 6 receives an input operation for adjusting the degree of suppression of the bone structure.

[0019] The display unit 7 displays a bone-suppressed tomographic image 20 and a bone-present tomographic image 21 (see FIG. 4) generated by an image processing unit 9, which will be described later. The display unit 7 includes, for example, a liquid crystal monitor.

[0020] The storage unit 8 is configured, for example, by a storage device such as a hard disk drive. The storage unit 8 stores image data such as an X-ray image 10 and a bone-suppressed tomographic image 20 (see FIG. 3) generated by an image processing unit 9, which will be described later. The storage unit 8 is also configured to store various setting values ​​for operating the X-ray imaging system 100. The storage unit 8 also stores a program used in the control process of the X-ray imaging system 100 by the image processing unit 9. The storage unit 8 also stores in advance a trained model 81, which will be described later.

[0021] The image processing unit 9 is a computer including, for example, a CPU, a GPU (Graphics Processing Unit), a ROM (Read Only Memory), and a RAM (Random Access Memory). In the first embodiment, the image processing unit 9 generates a tomographic image showing a cross section of the subject 101 by performing bone structure suppression processing (bone suppression processing) and reconstruction processing based on a plurality of X-ray images 10 (see FIG. 3) generated by performing X-ray imaging (tomosynthesis imaging). Specifically, the image processing unit 9 is configured to generate a bone-suppressed tomographic image 20 (see FIG. 3), which is a tomographic image in which bone structures in the chest and abdomen are suppressed. In the first embodiment, the bone structures of the ribs are suppressed by the bone suppression processing.

[0022] 2, the image processing unit 9 includes, as functional components, an X-ray image generation unit 91, a bone suppression processing unit 92, a reconstruction processing unit 93, an adjustment processing unit 94, and an image output unit 95. That is, the X-ray image generation unit 91, the bone suppression processing unit 92, the reconstruction processing unit 93, the adjustment processing unit 94, and the image output unit 95 are functional blocks as software in the image processing unit 9, and are configured to function when the image processing unit 9 as hardware executes a predetermined control program.

[0023] 3, the X-ray image generating unit 91 (image processing unit 9) acquires detection signals (image signals) of X-rays detected by the X-ray detection unit 3. Then, the X-ray image generating unit 91 generates an X-ray image 10 based on the acquired detection signals. The X-ray image 10 is an image generated by X-ray imaging of the chest and abdomen of a subject 101.

[0024] In the first embodiment, the bone suppression processing unit 92 (image processing unit 9) is configured to perform a process of suppressing bone structures in the chest and abdomen (bone suppression processing) based on a plurality of X-ray images 10 generated by performing tomosynthesis imaging. In the first embodiment, the bone suppression processing unit 92 performs a process of suppressing bone structures (ribs) on each of the plurality of X-ray images 10 before the reconstruction processing by the reconstruction processing unit 93, which will be described later, thereby generating a plurality of bone-suppressed X-ray images 11 in which the ribs are suppressed from the plurality of X-ray images 10. Details of the bone suppression processing by the bone suppression processing unit 92 will be described later. The bone-suppressed X-ray image 11 is an example of a "post-bone-suppression image" in the claims.

[0025] In the first embodiment, the reconstruction processing unit 93 (image processing unit 9) is configured to generate a bone-suppressed tomographic image 20 by performing a reconstruction process for generating a tomographic image based on a plurality of bone-suppressed X-ray images 11, which are a plurality of X-ray images 10 in which ribs are suppressed. Furthermore, the reconstruction processing unit 93 performs a reconstruction process based on a plurality of adjusted bone-suppressed X-ray images 11a (see FIG. 8), which are X-ray images 10 in which the degree of bone structure suppression has been adjusted by an adjustment processing unit 94 (described later), in order to adjust the degree of bone structure suppression in the generated bone-suppressed tomographic image 20. Thus, the reconstruction processing unit 93 generates an adjusted bone-suppressed tomographic image 20a, which is a bone-suppressed tomographic image 20 in which the degree of bone structure suppression has been adjusted. Furthermore, the reconstruction processing unit 93 is configured to generate a bone-present tomographic image 21 (see FIG. 4) by performing a reconstruction process on a plurality of X-ray images 10 before the bone structure suppression process has been performed. The tomographic image 21 with bones is an image (an image including the bone structure of the ribs) in which artifacts of the ribs appear in the lung area where no ribs exist in the cross section of the subject 101. The reconstruction process by the reconstruction processor 93 will be described in detail later.

[0026] The adjustment processing unit 94 (image processing unit 9) adjusts the degree of suppression of bone structures in the generated bone-suppressed tomographic image 20. In the first embodiment, the adjustment processing unit 94 executes a process of adjusting the degree of suppression of bone structures for the multiple bone-suppressed X-ray images 11 generated by the bone suppression processing unit 92, thereby generating multiple adjusted bone-suppressed X-ray images 11a (see FIG. 8) in which the degree of suppression of bone structures has been adjusted. Details of the adjustment of the degree of suppression of bone structures will be described later.

[0027] As shown in FIG. 4, the image output unit 95 (image processing unit 9) outputs the bone-suppressed tomographic image 20 generated by the reconstruction processing unit 93. Specifically, the image output unit 95 displays the bone-suppressed tomographic image 20 on the display unit 7. Similarly, the image output unit 95 outputs the bone-present tomographic image 21 generated by the reconstruction processing unit 93 and displays it on the display unit 7. For example, the image output unit 95 displays the bone-suppressed tomographic image 20 and the bone-present tomographic image 21 side by side on the display unit 7.

[0028] (Tomosynthesis imaging) As shown in FIG. 5, the X-ray imaging apparatus 100a is an apparatus that performs tomosynthesis imaging. For example, the X-ray imaging apparatus 100a performs multiple X-ray imaging operations by moving the X-ray irradiator 2 in the X1 direction while changing the irradiation angle and by moving the X-ray detector 3 in the X2 direction. Specifically, the imaging control unit 5 controls the operation of the movement mechanism 4 to move the X-ray irradiator 2 from a position of −20 degrees in the X2 direction to a position of +20 degrees in the X1 direction, with the vertical direction of the subject 101 (the Z direction in FIG. 1) as the reference (0 degrees). The imaging control unit 5 also captures 41 X-ray images 10 by performing X-ray imaging for each degree of movement of the X-ray irradiator 2 from the −20 degree position to the +20 degree position. The imaging control unit 5 also rotates the irradiation angle of the X-ray irradiator 2 by one degree each around the Y direction as the X-ray irradiator 2 moves in the X1 direction. The imaging control unit 5 is configured to move the X-ray detection unit 3 in the X2 direction in accordance with the movement of the X-ray irradiation unit 2 in the X1 direction.

[0029] In this way, the X-ray imaging device 100a performs X-ray imaging at each of the different imaging positions (irradiation angles) from -20 degrees to +20 degrees, and captures 41 X-ray images 10. Then, the X-ray image generation unit 91 (image processing unit 9) of the image processing device 100b generates 41 X-ray images 10 based on the 41 detection signals (image signals) captured (detected) by the X-ray imaging device 100a.

[0030] (bone suppression treatment) As shown in FIG. 6, the bone suppression processing unit 92 (image processing unit 9) performs bone suppression processing, which is processing for suppressing bone structures, on each of the 41 X-ray images 10. Specifically, in the first embodiment, the bone suppression processing unit 92 (image processing unit 9) performs image processing using a trained model 81 generated by machine learning so as to suppress bone structures (perform bone suppression). In more detail, the bone suppression processing unit 92 performs image processing to suppress (remove) the bone structures of the ribs from the X-ray images 10 of the chest and abdomen of the subject 101, based on the trained model 81 generated by machine learning.

[0031] The trained model 81 is generated by machine learning using deep learning so as to generate a bone-suppressed X-ray image 11 in which the ribs are suppressed from the X-ray image 10. The trained model 81 is generated in advance by a learning device separate from the image processing device 100b and stored in the storage unit 8. The learning device generates the trained model 81 by machine learning using a plurality of teacher input images 10t and a plurality of teacher output images 11t as teacher data (training set). The teacher input image 10t is generated so as to simulate an X-ray image 10 obtained by capturing the chest and abdomen of the subject 101. The teacher output image 11t is an image from the teacher input image 10t in which the ribs have been suppressed (removed). The teacher input image 10t and the teacher output image 11t are generated so as to have the same conditions (size, etc.) as the X-ray image 10 used as input in inference using the trained model 81.

[0032] The trained model 81 is generated, for example, based on a Fully Convolution Network (FCN). The trained model 81 is generated by training the model to perform image transformation (image processing) that suppresses images of ribs from the X-ray image 10 by transforming pixels estimated to be ribs from among the pixels of the input chest and abdominal X-ray image 10 (replacing pixel values ​​of bone structures (bone parts) with pixel values ​​of soft tissues such as muscles).

[0033] The bone suppression processing unit 92 (image processing unit 9) generates 41 bone-suppressed X-ray images 11 by performing bone suppression processing using the trained model 81 on each of the 41 X-ray images 10.

[0034] (Reconstruction processing) As shown in FIG. 7, the reconstruction processing unit 93 (image processing unit 9) of the image processing device 100b reconstructs 41 bone-suppressed X-ray images 11 to generate a bone-suppressed tomographic image 20 of the subject 101 at an arbitrary height (thickness) direction among cross sections parallel to the detection plane of the X-ray detection unit 3 (cross sections parallel to the movement direction of the X-ray irradiator 2). In the first embodiment, the bone-suppressed tomographic image 20 is an image of a cross section at an arbitrary height (thickness) in the Z direction among cross sections of the subject 101 parallel to the XY plane of FIG. 1. The reconstruction processing by the reconstruction processing unit 93 uses an iterative image reconstruction method (IR), a filtered back projection method (FBP), a shift-and-add method, or the like. For example, the reconstruction processing by the reconstruction processing unit 93 can use a T-SMART (Tomosynthesis Shimadzu Artifact Reduction Technology) method, which is an application of the iterative method.

[0035] (Adjustment of suppression level) Here, in the bone-suppressed tomographic image 20 generated by the reconstruction processing unit 93, the suppression of bone structures may be excessive or insufficient. For example, if the suppression of bone structures is insufficient, bone structures (artifacts) remain in the bone-suppressed tomographic image 20. On the other hand, if the suppression of bone structures is too strong, the bone-suppressed tomographic image 20 may look unnatural, or parts other than the bone structures (such as pulmonary blood vessels) may also be suppressed. The X-ray imaging system 100 according to the first embodiment is configured to be able to adjust the degree of suppression of bone structures in the bone-suppressed tomographic image 20 based on an input operation by an operator such as a doctor who has checked the bone-suppressed tomographic image 20 displayed on the display unit 7, for example.

[0036] As shown in Figure 8, in the first embodiment, the adjustment processing unit 94 (image processing unit 9) is configured to adjust the degree of suppression of bone structures in the bone-suppressed tomographic image 20 based on a plurality of X-ray images 10 (pre-bone-suppression images) before the bone structure suppression processing unit 92 performs the process of suppressing bone structures and a plurality of bone-suppressed X-ray images 11 (post-bone-suppression images) after the bone structure suppression processing unit 92 performs the process of suppressing bone structures.

[0037] Specifically, the adjustment processing unit 94 executes a process for adjusting the degree of suppression of bone structures based on the plurality of bone-suppressed X-ray images 11 that are the results of processing by the bone suppression processing unit 92. That is, the adjustment processing unit 94 is configured to adjust the degree of suppression of bone structures in the bone-suppressed tomographic image 20 by executing a process for adjusting the degree of suppression of bone structures on the plurality of bone-suppressed X-ray images 11 before the reconstruction processing by the reconstruction processing unit 93 is executed.

[0038] Specifically, the adjustment processing unit 94 generates a plurality of bone-extracted images 12 by obtaining a difference between each of the plurality of X-ray images 10 before the bone structures are suppressed and each of the plurality of bone-suppressed X-ray images 11 after the bone structures are suppressed. That is, the adjustment processing unit 94 generates the bone-extracted images 12 by obtaining a difference between the X-ray images 10 before the bone structure suppression processing by the bone suppression processing unit 92 is performed and the bone-suppressed X-ray images 11 after the processing is performed. The adjustment processing unit 94 is configured to obtain a difference between the corresponding X-ray images 10 and the bone-suppressed X-ray images 11 before and after the bone structure suppression processing is performed from among the 41 X-ray images 10 and the 41 bone-suppressed X-ray images 11. The bone-extracted images 12 are images in which only the bone structures (ribs) are extracted from the target region of the subject 101.

[0039] Then, the adjustment processing unit 94 (image processing unit 9) performs constant multiplication processing on the generated bone extraction image 12. Specifically, in the first embodiment, the adjustment processing unit 94 is configured to adjust the degree of suppression of bone structures in the bone-suppressed tomographic image 20 based on a predetermined adjustment coefficient K. The adjustment processing unit 94 generates an adjusted bone extraction image 12a by multiplying each pixel value of the pixels constituting the generated bone extraction image 12 by the adjustment coefficient K. The adjustment processing unit 94 performs constant multiplication processing on each of the multiple bone extraction images 12 to generate multiple adjusted bone extraction images 12a. The adjustment processing unit 94 then generates an adjusted bone-suppressed X-ray image 11a by obtaining differences between the multiple X-ray images 10 and the multiple adjusted bone extraction images 12a. The adjusted bone-suppressed X-ray image 11a is a bone-suppressed X-ray image 11 in which the degree of suppression of bone structures has been changed based on the adjustment coefficient K in order to adjust the degree of suppression of bone structures in the bone-suppressed tomographic image 20. Then, the reconstruction processing unit 93 generates adjusted bone-suppressed tomographic images 20a, which are bone-suppressed tomographic images 20 with the degree of suppression of bone structures adjusted, by executing reconstruction processing on the plurality of adjusted bone-suppressed X-ray images 11a, in the same way as for the bone-suppressed X-ray images 11. The image output unit 95 displays the generated adjusted bone-suppressed tomographic images 20a and the bone-present tomographic images 21 side by side on the display unit 7, in the same way as for the bone-suppressed tomographic images 20 before the degree of suppression of bone structures was adjusted.

[0040] In addition, the adjustment process of the degree of suppression of bone structure by the adjustment processing unit 94 is performed as follows: where P is the pixel value of the generated X-ray image 10, S is the pixel value of the bone-suppressed X-ray image 11, and Sa is the pixel value of the adjusted bone-suppressed X-ray image 11a, and since the bone-extracted image 12 is the difference between the X-ray image 10 and the bone-suppressed X-ray image 11, the pixel value Sa of the adjusted bone-suppressed X-ray image 11a is expressed as shown in equation (1). Sa=PK·(PS)=(1-K)·P+K·S···(1) Therefore, even if calculation processing using the adjustment coefficient K is performed on the X-ray image 10 and the bone-suppressed X-ray image 11 without generating the bone-extracted image 12, it is possible to obtain a similar adjusted bone-suppressed X-ray image 11a.

[0041] Furthermore, when the adjustment coefficient K is greater than 1, the bone structures in the adjusted bone-extracted image 12a become darker (higher in intensity), and therefore the strength of bone structure suppression in the adjusted bone-suppressed X-ray image 11a becomes greater. Therefore, when the adjustment coefficient K is greater than 1, the adjustment processing unit 94 adjusts the bone-suppressed tomographic image 20 to have a greater degree of bone structure suppression. On the other hand, when the adjustment coefficient K is less than 1, the bone structures in the adjusted bone-extracted image 12a become thinner (lower in intensity), and therefore the strength of bone structure suppression in the adjusted bone-suppressed X-ray image 11a becomes smaller. Therefore, when the adjustment coefficient K is less than 1, the adjustment processing unit 94 adjusts the bone-suppressed tomographic image 20 to have a lesser degree of bone structure suppression. Note that when the adjustment coefficient K is set to 0, an adjusted bone-suppressed tomographic image 20a is generated in a state where bone structure suppression processing has not been performed. In this case, the generated adjusted bone-suppressed tomographic image 20a will be an image similar to the tomographic image 21 with bone.

[0042] Furthermore, in the first embodiment, the adjustment processing unit 94 (image processing unit 9) is configured to change the adjustment coefficient K based on an input operation received by the operation unit 6. For example, an operator such as a doctor adjusts the degree of suppression of the bone structure by performing an operation on the operation unit 6 to change the magnitude of the adjustment coefficient K while checking the pre-adjustment bone-suppressed tomographic image 20 displayed on the display unit 7. The adjustment processing unit 94 is configured to set the adjustment coefficient K based on the received input operation and to adjust the degree of suppression of the bone structure based on the set adjustment coefficient K.

[0043] 9, in the first embodiment, the adjustment processing unit 94 (image processing unit 9) is configured to be able to adjust the degree of suppression of bone structures so that it varies for each pixel in the generated bone-suppressed tomographic image 20. Specifically, the adjustment processing unit 94 acquires an adjustment region 20r, which is a region for adjusting the degree of suppression of bone structures, based on an input operation on the operation unit 6. Then, the adjustment processing unit 94 is configured to adjust (change) the degree of suppression of bone structures for pixels included in the region specified as the adjustment region 20r in the bone-suppressed tomographic image 20.

[0044] For example, an operator such as a doctor sets (selects) an area of ​​the bone-suppressed tomographic image 20 corresponding to a lung field as an adjustment area 20r based on an input operation to the operation unit 6. Furthermore, an adjustment coefficient K is set based on an input operation to the operation unit 6 to adjust (change) the degree of bone structure suppression in the lung field area (adjustment area 20r). The adjustment processing unit 94 executes a calculation process to adjust the degree of bone structure suppression described above only for pixels included in the set adjustment area 20r based on the set adjustment coefficient K. In this way, the adjustment processing unit 94 generates a bone-suppressed tomographic image 20 in which the degree of bone structure suppression is adjusted only for pixels included in the adjustment area 20r. Note that bone structure suppression may not be performed on pixels not included in the adjustment area 20r (the adjustment coefficient K may be set to 0).

[0045] (Image processing method according to the first embodiment) Next, a control processing flow relating to the image processing method according to the first embodiment will be described with reference to Fig. 10. Step 401 indicates control processing by the imaging control unit 5 of the X-ray imaging apparatus 100a, and steps 402 to 411 indicate control processing by the image processing unit 9 of the image processing device 100b.

[0046] First, in step 401, X-ray imaging (tomosynthesis imaging) is performed on the chest and abdomen (target region) of the subject 101 while the X-ray irradiation unit 2 and the X-ray detection unit 3 are moved.

[0047] Next, in step 402, a plurality of (41) X-ray images 10 are generated based on the detection signals (image signals) acquired by performing the tomosynthesis imaging in step 401.

[0048] Next, in step 403, a process for suppressing the bone structure of the ribs in the chest and abdomen is performed based on the generated 41 X-ray images 10. Specifically, a process for suppressing the bone structure is performed on the X-ray images 10, thereby generating 41 bone-suppressed X-ray images 11 in which the bone structure of the ribs is suppressed.

[0049] Next, in step 404, a reconstruction process is performed to generate a tomographic image based on the 41 bone-suppressed X-ray images 11, which are X-ray images 10 in which bone structures are suppressed. Specifically, the reconstruction process is performed on the bone-suppressed X-ray images 11 to generate a bone-suppressed tomographic image 20, which is a cross-sectional image showing a cross section of the subject 101 in which the bone structures of the ribs are suppressed. Furthermore, a reconstruction process is performed on the generated 41 X-ray images 10 to generate a bone-present tomographic image 21.

[0050] Next, in step 405, the generated bone-suppressed tomographic image 20 and bone-present tomographic image 21 are displayed on the display unit 7. Specifically, the bone-suppressed tomographic image 20 and the bone-present tomographic image 21 are displayed side by side on the display unit 7.

[0051] Next, in step 406, it is determined whether an input operation to the operation unit 6 for adjusting the degree of suppression of bone structures in the bone-suppressed tomographic image 20 has been received. Specifically, it is determined whether an input operation for changing the adjustment coefficient K for adjusting the degree of suppression of bone structures has been received. If it is determined that an input operation for adjusting the degree of suppression of bone structures has been received, the process proceeds to step 407. If it is not determined that an input operation for adjusting the degree of suppression of bone structures has been received, step 406 is repeated.

[0052] In step 407, differences are obtained between the multiple (41) X-ray images 10 generated in step 402 and the multiple (41) bone-suppressed X-ray images 11 generated in step 403. Specifically, by obtaining differences between the multiple X-ray images 10 and the multiple bone-suppressed X-ray images 11, multiple bone-extracted images 12 are generated.

[0053] Next, in step 408, a constant multiplication process is performed on the generated plurality of bone extraction images 12. Specifically, each pixel value of the pixels constituting the generated plurality of bone extraction images 12 is multiplied by the input adjustment coefficient K, thereby generating a plurality of adjusted bone extraction images 12a.

[0054] Next, in step 409, differences are obtained between the plurality (41) of X-ray images 10 generated in step 402 and the plurality (41) of adjusted bone-extracted images 12a generated in step 408. Specifically, by obtaining differences between the plurality of X-ray images 10 and the plurality of adjusted bone-extracted images 12a, a plurality of adjusted bone-suppressed X-ray images 11a are generated.

[0055] Next, in step 410, a reconstruction process is performed on the plurality of adjusted bone-suppressed X-ray images 11a. Specifically, by performing the reconstruction process on the adjusted bone-suppressed X-ray images 11a, an adjusted bone-suppressed tomographic image 20a is generated, which is a bone-suppressed tomographic image 20 in which the degree of suppression of the bone structure of the ribs has been adjusted. That is, based on the plurality of X-ray images 10 generated in step 402, a process of suppressing the bone structure in step 403 and a reconstruction process in step 404 are performed, and a process of adjusting the degree of suppression of the bone structure in steps 407 to 410 is performed, thereby generating an adjusted bone-suppressed tomographic image 20a in which the degree of suppression of the bone structure has been adjusted.

[0056] Next, in step 411, the adjusted bone-suppressed tomographic image 20a generated in step 410 and the bone-present tomographic image 21 generated in step 404 are displayed on the display unit 7. Specifically, the bone-suppressed tomographic image 20 and the bone-present tomographic image 21 are displayed side by side on the display unit 7.

[0057] In addition, in step 406, if an input operation to change the adjustment coefficient K and an input operation to set the adjustment region 20r are accepted, the process of adjusting the degree of suppression of the bone structure in steps 407 to 410 is performed only on pixels included in the set adjustment region 20r of the bone-suppressed tomographic image 20.

[0058] (Effects of the first embodiment) In the first embodiment, the following effects can be obtained.

[0059] As described above, the X-ray imaging system 100 of the first embodiment generates a bone-suppressed tomographic image 20, which is a tomographic image showing a cross section of the subject 101 in which bone structures (ribs) in the target region (thorax and abdomen) are suppressed. By performing a process for suppressing bone structures (bone suppression process), bone structures (artifacts) can be suppressed in the tomographic image. Therefore, it is possible to prevent ribs from appearing in areas of the generated tomographic image where ribs (bone portions) do not actually exist. As a result, when generating a tomographic image showing a cross section of the subject 101, it is possible to prevent a decrease in visibility of the target region (thorax and abdomen) due to artifacts of bone portions (ribs). Furthermore, by adjusting the degree of bone structure suppression in the generated bone-suppressed tomographic image 20, adjustment can be made so that the bone structures are more accurately suppressed if the degree of bone structure suppression is excessive or insufficient. As a result, it is possible to further prevent a decrease in visibility of the target region in the generated bone-suppressed tomographic image 20 (adjusted bone-suppressed tomographic image 20a).

[0060] Furthermore, in the first embodiment, the following additional effects can be obtained by configuring as follows.

[0061] That is, in the first embodiment, as described above, the bone suppression processing unit 92 (image processing unit 9) is configured to perform processing to suppress bone structures on the plurality of X-ray images 10 before the reconstruction processing is performed, and the adjustment processing unit 94 (image processing unit 9) is configured to perform processing to adjust the degree of bone structure suppression based on the bone-suppressed X-ray image 11 (image after bone suppression) that is the result of processing by the bone suppression processing unit 92, thereby adjusting the degree of bone structure suppression in the generated bone-suppressed tomographic image 20. With this configuration, the plurality of X-ray images 10 before the reconstruction processing are images captured at a predetermined imaging position (irradiation angle). Therefore, the processing to suppress the image of the ribs can be easily performed compared to when the processing to suppress the ribs is performed on the tomographic image after the reconstruction. Therefore, the bone-suppressed tomographic image 20 can be easily generated, and a decrease in visibility of the chest and abdominal region can be easily suppressed. Furthermore, since the processing to adjust the degree of bone structure suppression is performed based on the bone-suppressed X-ray image 11 that is the result of processing by the bone suppression processing unit 92, the degree of bone structure suppression can be adjusted by performing image processing. Therefore, the degree of suppression of the bone structure can be adjusted without changing (adjusting) the parameters of the calculation process of the bone structure suppression process itself, so the degree of suppression of the bone structure can be easily adjusted.

[0062] Furthermore, in the first embodiment, as described above, the adjustment processing unit 94 (image processing unit 9) is configured to adjust the degree of suppression of bone structures in the bone-suppressed tomographic image 20 based on the X-ray image 10 (pre-bone-suppression image) before the bone structure suppression processing unit 92 (image processing unit 9) executes the process of suppressing bone structures and the bone-suppressed X-ray image 11 (post-bone-suppression image) after the bone structure suppression processing unit 92 executes the process of suppressing bone structures. With this configuration, the degree of suppression of bone structures by the bone suppression processing unit 92 can be easily adjusted by using the X-ray image 10 and the bone-suppressed X-ray image 11 before and after the process of suppressing bone structures is executed. Therefore, the degree of suppression of bone structures in the generated bone-suppressed tomographic image 20 can be easily adjusted.

[0063] Furthermore, as described above, the first embodiment includes the operation unit 6 that accepts input operations to adjust the degree of bone structure suppression. The adjustment processing unit 94 (image processing unit 9) is configured to adjust the degree of bone structure suppression in the bone-suppressed tomographic image 20 based on a predetermined adjustment coefficient K, and is configured to set the adjustment coefficient K based on the input operation accepted by the operation unit 6. With this configuration, the adjustment coefficient K can be changed (adjusted) by input operations on the operation unit 6, making it easier to adjust the degree of bone structure suppression in the bone-suppressed tomographic image 20. Therefore, an operator such as a doctor can easily check the adjusted bone-suppressed tomographic image 20a while adjusting the degree of bone structure suppression, and can easily recognize changes in the degree of bone structure suppression. As a result, it is easy to recognize which areas in the image are suppressed as bone structures, thereby improving the visibility of the lesion site. Furthermore, for example, if an operator such as a doctor visually inspecting the generated bone-suppressed tomographic image 20 feels uneasy about the bone-suppressed tomographic image 20 in which the bone structure is suppressed, the adjustment coefficient K can be reduced to decrease (weaken) the suppression of the bone structure in the bone-suppressed tomographic image 20. Therefore, by reducing the adjustment coefficient K, the bone-suppressed tomographic image 20 can be adjusted to be closer to a tomographic image including the bone structure, so that even if an operator such as a doctor feels uneasy about the bone-suppressed tomographic image 20 in which the bone structure is suppressed, the bone-suppressed tomographic image 20 can be adjusted to be easy for the operator such as a doctor to view.

[0064] Furthermore, in the first embodiment, as described above, the adjustment processing unit 94 (image processing unit 9) is configured to be able to adjust the degree of bone structure suppression so that it varies for each pixel in the generated bone-suppressed tomographic image 20. With this configuration, it is possible to locally adjust the suppression of bone structures only for a portion (a partial region) of the bone-suppressed tomographic image 20, rather than for the entire bone-suppressed tomographic image 20. Therefore, it is possible to perform the suppression process only on the bone structures, while suppressing the execution of the bone structure suppression process on regions other than the bone structures. As a result, it is possible to perform the bone structure suppression process only on necessary regions, and to suppress the execution of the bone structure suppression process on unnecessary regions. Therefore, by checking the generated bone-suppressed tomographic image 20 (adjusted bone-suppressed tomographic image 20a), it is possible to more accurately examine the lesion site in the chest and abdominal region of the subject 101.

[0065] Furthermore, in the first embodiment, as described above, the bone suppression processing unit 92 (image processing unit 9) is configured to perform a process of suppressing bone structures on each of the plurality of generated X-ray images 10, the adjustment processing unit 94 (image processing unit 9) is configured to perform a process of adjusting the degree of bone structure suppression on the plurality of bone-suppressed X-ray images 11 in which the bone structures have been suppressed by the bone suppression processing unit 92, and the reconstruction processing unit 93 (image processing unit 9) is configured to perform a reconstruction process based on the plurality of adjusted bone-suppressed X-ray images 11a in which the degree of bone structure suppression has been adjusted by the adjustment processing unit 94, thereby generating an adjusted bone-suppressed tomographic image 20a in which the degree of bone structure suppression has been adjusted. With this configuration, the process of suppressing bone structures is performed on the X-ray images 10 rather than on the reconstructed tomographic images, so that the bone suppression process can be performed on the plurality of X-ray images 10 in a relatively constant state, compared to tomographic images in which the state changes depending on the height (thickness) position of the cross section of the subject 101. Therefore, the process of suppressing the bone structure can be executed with high precision, and the visibility of the lesion site in the generated bone-suppressed tomographic image 20 and the adjusted bone-suppressed tomographic image 20a can be improved with high precision.

[0066] Furthermore, in the first embodiment, as described above, the reconstruction processing unit 93 (image processing unit 9) is configured to generate bone-present sectional images 21, which are sectional images including bone structures in the thoracic and abdominal regions (target region), by performing reconstruction processing on a plurality of X-ray images 10, and includes a display unit 7 that displays the bone-present sectional images 21 including bone structures and the bone-suppressed sectional images 20 in which the bone structures are suppressed. With this configuration, an operator such as a doctor can easily compare the target region (thoracic and abdominal regions) of the subject 101 in which the bone structures (ribs) are suppressed with the target region (thoracic and abdominal regions) of the subject 101 including the ribs by visually checking the display unit 7 on which the bone-present sectional images 21 and the bone-suppressed sectional images 20 are displayed. Therefore, by comparing the bone-suppressed sectional images 20 and the bone-present sectional images 21 displayed on the display unit 7, it is possible to easily examine the lesion region in the thoracic and abdominal regions of the subject 101.

[0067] Furthermore, in the first embodiment, as described above, the target region includes the thorax and abdomen (chest and abdomen) of the subject 101, and the image processing unit 9 is configured to generate a bone-suppressed tomographic image 20 in which bone structures, including ribs, in the thorax and abdomen are suppressed. Here, when tomosynthesis imaging of the thorax and abdomen is performed, the ribs that surround the lungs may appear in the cross-sectional portion of the lungs (rib artifacts may occur). Therefore, the rib artifacts appearing in the cross-sectional portion of the lungs may reduce the visibility of lesions in the lungs, making lung examination (diagnosis) difficult. In contrast, in the first embodiment, the target region includes the thorax and abdomen of the subject 101, and the image processing unit 9 is configured to generate a bone-suppressed tomographic image 20 in which bone structures, including ribs, in the thorax and abdomen are suppressed. With this configuration, it is possible to generate a bone-suppressed tomographic image 20 in which ribs are suppressed in a tomographic image of the thorax and abdomen including the lungs, thereby suppressing the reduction in visibility of lesions in the lungs due to rib artifacts.

[0068] Furthermore, in the first embodiment, as described above, the bone suppression processing unit 92 (image processing unit 9) is configured to suppress the ribs (bone structures) in the target region (thorax and abdomen) by executing image processing using the trained model 81 generated by machine learning to suppress the bone structures (ribs). With this configuration, it is possible to generate the bone-suppressed tomographic image 20 in which the image of the ribs is suppressed with high accuracy by using the trained model 81 generated by machine learning. Furthermore, since the bone-suppressed tomographic image 20 can be generated by using the trained model 81, it is possible to generate the bone-suppressed tomographic image 20 by changing the software configuration that executes image processing from a device that performs conventional tomosynthesis imaging. Therefore, it is possible to generate the bone-suppressed tomographic image 20 from a device that performs conventional tomosynthesis imaging without changing either the imaging method or the device configuration. As a result, the device configuration does not become too complicated in order to generate a bone-suppressed tomographic image 20 in which the ribs are suppressed, and by using the trained model 81, it is possible to accurately generate a bone-suppressed tomographic image 20 in which the ribs are suppressed, thereby more easily and accurately suppressing the reduction in visibility of the chest and abdomen caused by rib artifacts.

[0069] (Effects of the image processing method of the first embodiment) The image processing method of the first embodiment can provide the following effects.

[0070] The image processing method of the first embodiment, configured as described above, generates a bone-suppressed tomographic image 20, which is a tomographic image showing a cross section of the subject 101 in which bone structures (ribs) in the target region (thorax and abdomen) are suppressed. This allows the bone structures (artifacts) to be suppressed in the tomographic image by performing a process for suppressing the bone structures (bone suppression process). Therefore, it is possible to prevent ribs from appearing in areas of the generated tomographic image where ribs (bone portions) do not actually exist. As a result, it is possible to provide an image processing method that can suppress a decrease in the visibility of the target region (thorax and abdomen) due to artifacts of bone portions (ribs) when generating a tomographic image showing a cross section of the subject 101. Furthermore, by adjusting the degree of bone structure suppression in the generated bone-suppressed tomographic image 20, it is possible to adjust the degree of bone structure suppression so that the bone structures are more accurately suppressed when the degree of bone structure suppression is excessive or insufficient. As a result, it is possible to provide an image processing method that can further suppress a decrease in the visibility of the target region in the generated bone-suppressed tomographic image 20 (adjusted bone-suppressed tomographic image 20a).

[0071] [Second embodiment] Next, an X-ray imaging system 200 according to a second embodiment will be described with reference to Figures 11 and 12. Unlike the first embodiment, which is configured to execute processing to suppress bone structures (ribs) on a plurality of X-ray images 10 before reconstruction processing is executed, the second embodiment is configured to execute processing to suppress bone structures (ribs) on a tomographic image 21 with bones, which is a tomographic image after reconstruction processing has been executed. Note that in the second embodiment, components similar to those in the first embodiment are designated by the same reference numerals, and descriptions thereof will be omitted.

[0072] As shown in FIG. 11 , an X-ray imaging system 200 of the second embodiment includes an X-ray imaging apparatus 100a and an image processing apparatus 200b. The image processing apparatus 200b includes an image processing unit 209. Similar to the image processing unit 9 of the first embodiment, the image processing unit 209 is configured to generate a bone-suppressed tomographic image 220 based on an X-ray image 10. In the second embodiment, the image processing unit 209 is configured to generate the bone-suppressed tomographic image 220 by executing a process of suppressing an image of a bone structure (ribs) on a bone-present tomographic image 21 after the reconstruction process has been executed. The image processing unit 209 also includes, as functional components, an X-ray image generation unit 91, a bone suppression processing unit 292, a reconstruction processing unit 293, an adjustment processing unit 294, and an image output unit 95.

[0073] As shown in Figure 12, the X-ray image generation unit 91 (image processing unit 209), as in the first embodiment, generates 41 X-ray images 10 based on detection signals (image signals) acquired by X-ray photography (tomosynthesis photography) using the X-ray photography device 100a.

[0074] The reconstruction processing unit 293 (image processing unit 209) is configured to perform reconstruction processing on a plurality of captured X-ray images 10 before suppressing bone structures (ribs) (before executing bone suppression processing), thereby generating bone-present tomographic images 21, which are tomographic images including bone parts (bone structures). The processing method of the reconstruction processing is the same as that in the first embodiment.

[0075] In the second embodiment, the bone suppression processing unit 292 (image processing unit 209) is configured to generate a bone-suppressed tomographic image 220 by executing a bone suppression process, which is a process of suppressing bone structures (ribs), on the tomographic image 21 with bones after the reconstruction process generated by the reconstruction processing unit 293 has been executed. For example, the bone suppression processing unit 292 generates a bone-suppressed tomographic image 220 in which ribs are suppressed from the tomographic image 21 with bones, which is a tomographic image including ribs, based on a trained model 281 (see FIG. 11 ) generated in advance by machine learning.

[0076] The trained model 281, like the trained model 81 in the first embodiment, is generated in advance by a learning device separate from the image processing device 200b and stored in the storage unit 8. That is, like the trained model 81 in the first embodiment, the trained model 281 is generated by learning to perform image transformation (image processing) that suppresses images of ribs from the input tomographic image 21 with bones by machine learning using deep learning.

[0077] The image output unit 95 (image processing unit 209) displays the generated bone-suppressed tomographic image 220 and the tomographic image 21 with bone on the display unit 7, similarly to the first embodiment.

[0078] Then, the adjustment processing unit 294 (image processing unit 209), like the adjustment processing unit 94 according to the first embodiment, is configured to execute processing for adjusting the degree of suppression of bone structures in the bone-suppressed tomographic image 220 generated by the bone suppression processing unit 292. In the second embodiment, the adjustment processing unit 294 is configured to adjust the degree of suppression of bone structures in the bone-suppressed tomographic image 220 based on the bone-present tomographic image 21, which is a pre-bone-suppression image before the bone structure suppression processing is executed by the bone suppression processing unit 292, and the bone-suppressed tomographic image 220, which is a post-bone-suppression image after the bone structure suppression processing is executed by the bone suppression processing unit 292.

[0079] In the second embodiment, an adjustment coefficient K is acquired based on an input operation on the operation unit 6, as in the first embodiment. Then, the adjustment processing unit 294 adjusts the degree of suppression of bone structures in the bone-suppressed tomographic image 220 based on the acquired adjustment coefficient K. First, the adjustment processing unit 294 acquires the difference between the generated bone-present tomographic image 21 and the bone-suppressed tomographic image 20, thereby generating a bone-extracted tomographic image 222. The bone-extracted tomographic image 222 is an image in which only bone structure components are extracted from the bone-present tomographic image 21.

[0080] The adjustment processing unit 294 then performs constant multiplication processing on the generated bone-extracted tomographic image 222, as in the first embodiment. The adjustment processing unit 294 generates an adjusted bone-extracted tomographic image 222a by multiplying each pixel value of the pixels constituting the generated bone-extracted tomographic image 222 by an adjustment coefficient K. The adjustment processing unit 294 then obtains the difference between the generated adjusted bone-extracted tomographic image 222a and the bone-present tomographic image 21, thereby generating an adjusted bone-suppressed tomographic image 220a, which is the bone-suppressed tomographic image 220 in which the degree of suppression of the bone structure has been adjusted. As in the first embodiment, the image output unit 95 displays the generated adjusted bone-suppressed tomographic image 220a alongside the bone-present tomographic image 21 on the display unit 7.

[0081] The other configurations of the second embodiment are the same as those of the first embodiment.

[0082] (Effects of the second embodiment) In the second embodiment, the following effects can be obtained.

[0083] In the second embodiment, as described above, the bone suppression processing unit 292 (image processing unit 209) is configured to perform processing to suppress bone structures (ribs) on the tomographic image (bone-present tomographic image 21) after the reconstruction processing has been performed. Also, in the second embodiment, as described above, the reconstruction processing unit 293 (image processing unit 209) is configured to perform reconstruction processing on the plurality of captured X-ray images 10 to generate the bone-present tomographic image 21, which is a tomographic image including bone structures in the chest and abdomen (target region), the bone suppression processing unit 292 (image processing unit 209) is configured to perform processing to suppress ribs (bone structures) on the bone-present tomographic image 21 generated by the reconstruction processing unit 293, to generate the bone-suppressed tomographic image 220, and the adjustment processing unit 294 (image processing unit 209) is configured to perform processing to adjust the degree of suppression of bone structures on the bone-suppressed tomographic image 220 generated by the bone suppression processing unit 292. With this configuration, similar to the first embodiment, by adjusting the degree of suppression of the bone structure in the generated bone-suppressed tomographic image 220, if the degree of suppression of the bone structure is excessive or insufficient, the bone structure can be more accurately suppressed. As a result, in the generated bone-suppressed tomographic image 220 (adjusted bone-suppressed tomographic image 220a), a decrease in the visibility of the target region can be further suppressed. Note that other effects of the second embodiment are similar to those of the first embodiment.

[0084] [Third embodiment] Next, an X-ray imaging system 300 according to a third embodiment will be described with reference to Figures 13 and 14. In the third embodiment, the degree of suppression of bone structures in the bone-suppressed tomographic image 20 is adjusted based on a bone-present tomographic image 21, which is a tomographic image obtained after reconstruction processing has been performed, and a bone-extracted tomographic image 322, which is a tomographic image in which bone structures have been extracted. In the third embodiment, components similar to those in the first embodiment are denoted by the same reference numerals, and descriptions thereof will be omitted.

[0085] 13, an X-ray imaging system 300 of the third embodiment includes an X-ray imaging apparatus 100a and an image processing apparatus 300b. The image processing apparatus 300b includes an image processing unit 309. Similar to the image processing unit 9 of the first embodiment, the image processing unit 309 is configured to generate a bone-suppressed tomographic image 20 based on an X-ray image 10. The image processing unit 309 also includes, as functional components, an X-ray image generation unit 91, a bone suppression processing unit 92, a reconstruction processing unit 393, an adjustment processing unit 394, and an image output unit 95.

[0086] 14, the X-ray image generation unit 91 (image processing unit 309) generates 41 X-ray images 10 based on detection signals (image signals) acquired by X-ray photography (tomosynthesis photography) using the X-ray imaging device 100a, as in the first embodiment. Also, the bone suppression processing unit 92 (image processing unit 309) generates multiple bone-suppressed X-ray images 11 by performing a process (bone suppression process) to suppress bone structures using the trained model 81 on the multiple generated X-ray images 10, as in the first embodiment.

[0087] The reconstruction processing unit 393 (image processing unit 309) is configured to perform reconstruction processing on a plurality of bone-suppressed X-ray images 11, as in the first embodiment, to generate a bone-suppressed tomographic image 20 (see FIG. 3) similar to that in the first embodiment. Similarly to the first embodiment, the reconstruction processing unit 393 is configured to perform reconstruction processing on a plurality of X-ray images 10, to generate a bone-present tomographic image 21. In the third embodiment, the reconstruction processing unit 393 is configured to perform reconstruction processing on a plurality of bone-extracted images 12 (see FIG. 14) generated by an adjustment processing unit 394 (described later) to adjust the degree of suppression of bone structures in the generated bone-suppressed tomographic image 20, to generate a bone-extracted tomographic image 322 (see FIG. 14). The bone-extracted tomographic image 322 is a tomographic image in which only components of the bone structure of the subject 101 are extracted. The reconstruction processing method is the same as that in the first embodiment.

[0088] The image output unit 95 (image processing unit 309) displays the generated bone-suppressed tomographic image 20 and bone-present tomographic image 21 on the display unit 7, similarly to the first embodiment.

[0089] The adjustment processing unit 394 (image processing unit 309), like the adjustment processing unit 94 in the first embodiment, is configured to perform processing on the bone-suppressed tomographic image 20 generated by the reconstruction processing unit 393 to adjust the degree of suppression of the bone structure in the bone-suppressed tomographic image 20.

[0090] In the third embodiment, similarly to the first embodiment, an adjustment coefficient K is acquired based on an input operation on the operation unit 6. Then, the adjustment processing unit 394 adjusts the degree of suppression of bone structures in the bone-suppressed tomographic image 20 based on the acquired adjustment coefficient K. First, similarly to the first embodiment, the adjustment processing unit 394 generates a plurality of bone-extracted images 12 based on a plurality of X-ray images 10 and bone-suppressed X-ray images 11, which are the plurality of X-ray images 10 in which bone structures have been suppressed by the bone suppression processing unit 92. Specifically, the adjustment processing unit 394 generates a plurality of bone-extracted images 12 by acquiring a difference between each of the plurality of X-ray images 10 and each of the bone-suppressed X-ray images 11. The bone-extracted images 12 are images in which bone structures in the chest and abdominal region of the subject 101 have been extracted.

[0091] Then, the adjustment processing unit 394 performs constant multiplication processing on the bone extraction tomographic image 322 generated by the reconstruction processing unit 393 performing reconstruction processing on the bone extraction image 12, in the same manner as in the first embodiment. Specifically, the adjustment processing unit 394 multiplies each of the pixel values ​​of the pixels constituting the generated bone extraction tomographic image 322 by the adjustment coefficient K to generate an adjusted bone extraction tomographic image 322a.

[0092] In the third embodiment, the adjustment processing unit 394 is configured to generate an adjusted bone-suppressed tomographic image 320a, which is a bone-suppressed tomographic image 20 in which the degree of suppression of bone structures has been adjusted, based on the bone-present tomographic image 21 and the bone-extracted tomographic image 322. Specifically, the adjustment processing unit 394 generates the adjusted bone-suppressed tomographic image 320a by obtaining the difference between the generated adjusted bone-extracted tomographic image 322a and the bone-present tomographic image 21. As in the first embodiment, the image output unit 95 displays the generated adjusted bone-suppressed tomographic image 320a alongside the bone-present tomographic image 21 on the display unit 7.

[0093] The other configurations of the third embodiment are the same as those of the first embodiment.

[0094] (Effects of the third embodiment) In the third embodiment, the following effects can be obtained.

[0095] In the third embodiment, as described above, the bone suppression processing unit 92 (image processing unit 309) is configured to perform processing to suppress bone structures on each of the multiple X-ray images 10 generated, and the reconstruction processing unit 393 (image processing unit 309) is configured to perform reconstruction processing on the multiple X-ray images 10 to generate a bone-present tomographic image 21, which is a tomographic image including bone structures in the thorax and abdomen (target region), and to perform reconstruction processing on multiple bone-extracted images 12, in which bone structures in the thorax and abdomen are extracted, generated based on the multiple X-ray images 10 and bone-suppressed X-ray images 11, which are multiple X-ray images 10 in which bone structures are suppressed by the bone suppression processing unit 92, to generate a bone-extracted tomographic image 322, which is a tomographic image in which bone structures in the thorax and abdomen are extracted, and the adjustment processing unit 394 (image processing unit 309) is configured to generate an adjusted bone-suppressed tomographic image 320a in which the degree of suppression of bone structures is adjusted based on the bone-present tomographic image 21 and the bone-extracted tomographic image 322. With this configuration, similar to the first embodiment, by adjusting the degree of suppression of the bone structure in the generated bone-suppressed tomographic image 20, if the degree of suppression of the bone structure is excessive or insufficient, the bone structure can be more accurately suppressed. As a result, in the generated bone-suppressed tomographic image 20 (adjusted bone-suppressed tomographic image 320a), a decrease in the visibility of the target region can be further suppressed. Note that other effects of the third embodiment are similar to those of the first embodiment.

[0096] [Variations] The embodiments disclosed herein should be considered to be illustrative and not restrictive in all respects. The scope of the present invention is defined by the claims, not by the description of the above embodiments, and includes all modifications (variations) within the meaning and scope of the claims.

[0097] For example, in the above first to third embodiments, an example has been shown in which the image processing unit 9 (209, 309) is configured to generate a bone-suppressed tomographic image 20 (220) in which ribs are suppressed in the thoracic and abdominal regions (chest and abdomen), but the present invention is not limited to this. In the present invention, the image processing unit 9 (209, 309) may be configured to generate a bone-suppressed tomographic image in which bone structures including ribs are suppressed in either the thoracic or abdominal regions. Also, in the present invention, the image processing unit 9 (209, 309) may be configured to generate a bone-suppressed tomographic image in which the femur is suppressed in angiography of the lower limbs. Also, the image processing unit 9 (209, 309) may be configured to execute processing to suppress the spine and clavicle in addition to the ribs in the thoracic and abdominal regions.

[0098] In the first to third embodiments, an example is shown in which a bone-suppressed tomographic image 20 (220) in which bone structures (ribs) are suppressed is generated by executing image processing using a trained model 81 (281) generated by machine learning, but the present invention is not limited to this. For example, a process of extracting bones and suppressing bone structures may be executed using a rule-based algorithm (e.g., template matching). Also, a dual energy subtraction (DES) method may be used to suppress bone structures based on X-ray images generated using X-rays of two different energies.

[0099] Furthermore, in the above-described first and third embodiments, an example was shown in which a common trained model 81 was used to perform processing to suppress bone structures (ribs) for each of 41 X-ray images 10, but the present invention is not limited to this. For example, a configuration may be used in which processing to suppress bone structures is performed using multiple trained models that are trained to correspond to different imaging positions (irradiation angles). In this case, 41 different trained models may be used for each irradiation angle so as to correspond to the 41 X-ray images 10. Alternatively, four or five trained models may be used, and the trained model may be changed for each of multiple irradiation angles.

[0100] In the first to third embodiments, the image processing device 100b (200b, 300b) is provided with a display unit 7 that displays the bone-suppressed tomographic image 20 (220) and the adjusted bone-suppressed tomographic image 20a (220a, 320a), but the present invention is not limited to this. For example, the generated bone-suppressed tomographic image 20 (220) and the adjusted bone-suppressed tomographic image 20a (220a, 320a) may be displayed on a display unit provided in the X-ray imaging device 100a. Furthermore, the generated bone-suppressed tomographic image 20 (220) and the adjusted bone-suppressed tomographic image 20a (220a, 320a) may be output to an external display device other than the image processing device 100b (200b, 300b), thereby displaying the bone-suppressed tomographic image 20 (220) and the adjusted bone-suppressed tomographic image 20a (220a, 320a) on the external display device.

[0101] In the first to third embodiments, the bone-present tomographic image 21 and the bone-suppressed tomographic image 20 (220) or the adjusted bone-suppressed tomographic image 20a (220a, 320a) are displayed side by side on the display unit 7. However, the present invention is not limited to this. For example, the X-ray image 10 and the bone-suppressed tomographic image 20 (220) or the adjusted bone-suppressed tomographic image 20a (220a, 320a) may be displayed side by side. Also, the X-ray image 10 in which bone structure is not suppressed and the bone-suppressed X-ray image 11 in which bone structure is suppressed may be displayed side by side on the display unit 7. Furthermore, the display of the bone-suppressed tomographic image 20 (220) and the adjusted bone-suppressed tomographic image 20a (220a, 320a) may be switched based on an input operation on the operation unit 6.

[0102] In the first to third embodiments, the imaging control unit 5 and the image processing unit 9 (209, 309) are configured as separate pieces of hardware, and the imaging control unit 5 and the image processing unit 9 (209, 309) respectively perform control processing for X-ray imaging and control processing for generating the bone-suppressed tomographic image 20 (220) and the adjusted bone-suppressed tomographic image 20a (220a, 320a). However, the present invention is not limited to this. For example, a single common control unit (hardware) may be configured to perform X-ray imaging and the generation of the bone-suppressed tomographic image 20 (220) and the adjusted bone-suppressed tomographic image 20a (220a, 320a). In this case, the X-ray imaging (tomosynthesis imaging) and the image processing for generating the bone-suppressed tomographic image 20 (220) and the adjusted bone-suppressed tomographic image 20a (220a, 320a) may be performed by a single device.

[0103] Furthermore, in the above first to third embodiments, an example has been shown in which the X-ray image generation unit 91, the bone suppression processing unit 92 (292), the reconstruction processing unit 93 (293, 393), the adjustment processing unit 94 (294, 394), and the image output unit 95 are configured as functional blocks (software) in one piece of hardware (image processing unit 9), but the present invention is not limited to this. For example, the X-ray image generation unit 91, the bone suppression processing unit 92 (292), the reconstruction processing unit 93 (293, 393), the adjustment processing unit 94 (294, 394), and the image output unit 95 may each be configured by separate hardware (arithmetic circuits).

[0104] In the above first to third embodiments, an example has been shown in which tomosynthesis imaging is performed on the chest and abdomen (target region) of the subject 101 while moving the X-ray irradiator 2 and the X-ray detector 3, but the present invention is not limited to this. For example, tomosynthesis imaging may be performed by moving only the X-ray irradiator 2.

[0105] In the first to third embodiments, the X-ray irradiator 2 is held by a pillar-shaped irradiator holder 4a, but the present invention is not limited to this. For example, the X-ray irradiator 2 may be a ceiling-mounted type. Furthermore, the X-ray irradiator 2 and the X-ray detector 3 may be held by a C-arm.

[0106] In the first to third embodiments, when performing tomosynthesis imaging, the X-ray irradiator 2 is moved from a position of -20 degrees to a position of +20 degrees with the vertical direction of the subject 101 as the reference (0 degrees), but the present invention is not limited to this. For example, the X-ray irradiator 2 may be moved from a position of -15 degrees to a position of +15 degrees.

[0107] In the first to third embodiments, an example has been shown in which, when performing tomosynthesis imaging, 41 X-ray images 10 are captured by performing X-ray imaging every time the X-ray irradiator 2 moves by one degree, but the present invention is not limited to this. For example, X-ray imaging may be performed every time the X-ray irradiator 2 moves by two degrees, or every time it moves by 0.5 degrees.

[0108] In addition, in the first to third embodiments, an example was shown in which the operation unit 6 is provided to receive an input operation for setting the adjustment coefficient K to adjust the degree of suppression of the bone structure, but the present invention is not limited to this. For example, the degree of suppression of the bone structure may be adjusted by a predetermined adjustment coefficient K that is set in advance.

[0109] Furthermore, in the above-described first to third embodiments, examples have been shown in which bone suppression processing or reconstruction processing is performed on a plurality of X-ray images 10 acquired by tomosynthesis imaging, but the present invention is not limited to this. For example, before performing bone suppression processing on a plurality of X-ray images 10 acquired by tomosynthesis imaging, preprocessing for adjusting image quality may be performed. Specifically, preprocessing such as contrast adjustment, resolution adjustment, or noise removal may be performed on the acquired X-ray images 10. Furthermore, when preprocessing is performed on the X-ray images 10, the parameters of the preprocessing may be configured to be adjustable by the user.

[0110] In the first to third embodiments, an example has been shown in which a region corresponding to the lung field in the bone-suppressed tomographic image 20 (220) is set as the adjustment region 20r for varying the degree of suppression of the bone structure for each pixel based on an input operation on the operation unit 6, but the present invention is not limited to this. For example, only a part of the lung field (for example, only the right lung) may be set as the adjustment region 20r, rather than the entire lung field. Furthermore, the degree of suppression for each pixel may be adjusted by decreasing the adjustment coefficient K so that the region spreads concentrically from coordinates specified based on an input operation on the operation unit 6.

[0111] Furthermore, in the above first to third embodiments, an example has been shown in which an input operation for setting the adjustment region 20r and the adjustment coefficient K is accepted when the bone-suppressed tomographic image 20 (220) is displayed on the display unit 7, but the present invention is not limited to this. For example, the configuration may be such that an input operation for setting the adjustment region 20r and the adjustment coefficient K by an operator such as a doctor is accepted when a tomographic image in which bone structure is not suppressed (tomographic image 21 with bone) is displayed on the display unit 7.

[0112] [Aspect] It will be appreciated by those skilled in the art that the exemplary embodiments described above are examples of the following aspects.

[0113] (Item 1) an X-ray irradiation unit that irradiates a target area of ​​the subject with X-rays; an X-ray detection unit that detects X-rays irradiated from the X-ray irradiation unit; a movement mechanism that moves at least one of the X-ray irradiation unit and the X-ray detection unit; an imaging control unit that performs X-ray imaging of the target region of the subject while moving at least one of the X-ray irradiation unit and the X-ray detection unit using the movement mechanism; an image processing unit that generates a bone-suppressed tomographic image, which is a tomographic image showing a cross section of the subject in which a bone structure in the target region is suppressed, based on a plurality of X-ray images generated by performing the X-ray photography; The image processing unit a bone suppression processing unit that executes a process of suppressing the bone structure in the target region based on the generated plurality of X-ray images; a reconstruction processing unit that performs reconstruction processing to generate the tomographic image based on the generated plurality of X-ray images; an adjustment processing unit that adjusts the degree of suppression of the bone structure in the generated bone-suppressed tomographic image.

[0114] (Item 2) the bone suppression processing unit is configured to perform a process of suppressing the bone structure on either the plurality of X-ray images before the reconstruction process is performed or the tomographic image after the reconstruction process is performed; The X-ray imaging system described in item 1, wherein the adjustment processing unit is configured to adjust the degree of suppression of the bone structure in the generated bone-suppressed tomographic image by performing a process to adjust the degree of suppression of the bone structure based on a post-bone suppression image that is the result of processing by the bone suppression processing unit.

[0115] (Item 3) The X-ray imaging system described in item 2, wherein the adjustment processing unit is configured to adjust the degree of suppression of the bone structure in the bone-suppressed tomographic image based on a pre-bone-suppression image before the bone structure suppression processing unit performs the process of suppressing the bone structure and a post-bone-suppression image after the bone structure suppression processing unit performs the process of suppressing the bone structure.

[0116] (Item 4) an operation unit that receives an input operation to adjust the degree of suppression of the bone structure; The X-ray imaging system according to any one of items 1 to 3, wherein the adjustment processing unit is configured to adjust the degree of suppression of the bone structure in the bone-suppressed tomographic image based on a predetermined adjustment coefficient, and is configured to set the adjustment coefficient based on an input operation received by the operation unit.

[0117] (Item 5) The X-ray imaging system according to any one of items 1 to 4, wherein the adjustment processing unit is configured to be able to adjust the degree of suppression of the bone structure so that it differs for each pixel in the generated bone-suppressed tomographic image.

[0118] (Item 6) the bone suppression processing unit is configured to perform a process of suppressing the bone structure on each of the generated X-ray images; the adjustment processing unit is configured to execute a process of adjusting a degree of suppression of the bone structures for the plurality of X-ray images in which the bone structures have been suppressed by the bone suppression processing unit, The X-ray imaging system according to any one of items 1 to 5, wherein the reconstruction processing unit is configured to generate the bone-suppressed tomographic image in which the degree of suppression of the bone structure has been adjusted by executing the reconstruction processing based on the plurality of X-ray images in which the degree of suppression of the bone structure has been adjusted by the adjustment processing unit.

[0119] (Item 7) the reconstruction processing unit is configured to generate a tomographic image with bone, which is the tomographic image including the bone structure in the target region, by executing a reconstruction process on the plurality of X-ray images; the bone suppression processing unit is configured to generate the bone-suppressed tomographic image by executing a process of suppressing the bone structure on the tomographic image with bone generated by the reconstruction processing unit, The X-ray imaging system according to any one of items 1 to 5, wherein the adjustment processing unit is configured to perform processing to adjust the degree of suppression of the bone structure for the bone-suppressed tomographic image generated by the bone suppression processing unit.

[0120] (Item 8) the bone suppression processing unit is configured to perform a process of suppressing the bone structure on each of the generated X-ray images; the reconstruction processing unit is configured to generate bone-present tomographic images, which are tomographic images including the bone structures in the target region, by executing a reconstruction process on the plurality of X-ray images, and to generate bone-extracted tomographic images, which are tomographic images from which the bone structures in the target region have been extracted, by executing a reconstruction process on a plurality of bone-extracted images, which are tomographic images from which the bone structures in the target region have been extracted, generated based on the plurality of X-ray images and the plurality of X-ray images from which the bone structures have been suppressed by the bone suppression processing unit; The X-ray imaging system according to any one of items 1 to 5, wherein the adjustment processing unit is configured to generate the bone-suppressed tomographic image in which the degree of suppression of the bone structure is adjusted based on the bone-present tomographic image and the bone-extracted tomographic image.

[0121] (Item 9) the reconstruction processing unit is configured to generate a tomographic image with bone, which is the tomographic image including the bone structure in the target region, by executing a reconstruction process on the plurality of X-ray images; 9. The X-ray imaging system according to any one of items 1 to 8, further comprising a display unit that displays the bone-present tomographic image including the bone structure and the bone-suppressed tomographic image in which the bone structure is suppressed.

[0122] (Item 10) the target site includes at least one of a chest and an abdomen of the subject; The X-ray imaging system according to any one of items 1 to 9, wherein the image processing unit is configured to generate the bone-suppressed tomographic image in which the bone structures including ribs are suppressed in at least one of the chest and the abdomen.

[0123] (Item 11) 11. The X-ray imaging system according to any one of items 1 to 10, wherein the bone suppression processing unit is configured to suppress the bone structures in the target region by performing image processing using a trained model generated by machine learning to suppress the bone structures.

[0124] (Item 12) generating a plurality of X-ray images by performing X-ray imaging on a target region of a subject while moving at least one of an X-ray irradiator that irradiates X-rays onto the target region of the subject and an X-ray detector that detects the X-rays irradiated from the X-ray irradiator; generating a bone-suppressed tomographic image, which is a tomographic image showing a cross section of the subject in which a bone structure in the target region is suppressed, based on the plurality of X-ray images generated by performing the X-ray photography; The step of generating the bone-suppressed tomographic image includes: performing a process of suppressing the bone structure in the target region based on the generated plurality of X-ray images; performing a reconstruction process to generate the tomographic image based on the generated plurality of X-ray images; and adjusting the degree of suppression of the bone structure in the generated bone-suppressed tomographic image. [Explanation of symbols]

[0125] 2 X-ray irradiation section 3 X-ray detection unit 4 Moving mechanism 5. Shooting control unit 6 Control section 7 Display section 9, 209, 309 Image processing unit 10 X-ray images (images before bone suppression) 11 Bone suppression X-ray image (image after bone suppression) 12 Bone extraction image 20 Bone suppression tomography images 20a, 220a, 320a Adjusted bone suppression tomographic images (bone suppression tomographic images) 21 Cross-sectional image with bone (image before bone suppression) 81, 281 trained models 92, 292 Bone suppression processing section 93, 293, 393 Reconstruction processing unit 94, 294, 394 Adjustment processing section 100, 200, 300 X-ray systems 101 Subject 220 Bone suppression tomographic image (image after bone suppression) 322 Bone Extraction Tomography

Claims

1. an X-ray irradiation unit that irradiates a target region of a subject with X-rays; an X-ray detection unit that detects X-rays irradiated from the X-ray irradiation unit; a movement mechanism that moves at least one of the X-ray irradiation unit and the X-ray detection unit; an imaging control unit that performs tomosynthesis imaging of the target region of the subject while moving at least one of the X-ray irradiation unit and the X-ray detection unit using the movement mechanism; an image processing unit that generates a bone-suppressed tomographic image, which is a tomographic image showing a cross section of the subject in which a bone structure in the target region is suppressed, based on a plurality of X-ray images generated by performing the tomosynthesis imaging; The image processing unit a bone suppression processing unit that executes a process of suppressing the bone structure in the target region using a trained model that has been trained using teacher input images including bone structures and teacher output images in which the bone structures have been suppressed or removed from the teacher input images, based on the generated plurality of X-ray images; a reconstruction processing unit that performs reconstruction processing to generate the tomographic image based on the generated plurality of X-ray images; an adjustment processing unit that adjusts the degree of suppression of bone structures in the generated bone-suppressed tomographic image.

2. the bone suppression processing unit is configured to perform a process of suppressing a bone structure on either the plurality of X-ray images before the reconstruction process is performed or the tomographic image after the reconstruction process is performed; 2. The X-ray imaging system according to claim 1, wherein the adjustment processing unit is configured to adjust the degree of suppression of bone structures in the generated bone-suppressed tomographic image by performing a process of adjusting the degree of suppression of bone structures based on a post-bone suppression image that is a result of processing by the bone suppression processing unit.

3. 3. The X-ray imaging system of claim 2, wherein the adjustment processing unit is configured to adjust the degree of suppression of bone structures in the bone-suppressed tomographic image based on a pre-bone-suppression image before the bone structure suppression processing is performed by the bone suppression processing unit and a post-bone-suppression image after the bone structure suppression processing is performed by the bone suppression processing unit.

4. The bone suppression processing unit is configured to generate a plurality of bone-suppressed X-ray images by performing a process of suppressing bone structures on each of the plurality of X-ray images using the trained model; The X-ray imaging system according to claim 1 , wherein the reconstruction processing unit executes reconstruction processing for generating the tomographic image based on the plurality of bone-suppressed X-ray images.

5. The method further comprises an operation unit that receives an input operation to adjust the degree of the suppression of the bone structure; 2. The X-ray imaging system according to claim 1, wherein the adjustment processing unit is configured to adjust the degree of suppression of bone structures in the bone-suppressed tomographic image based on a predetermined adjustment coefficient, and is configured to set the adjustment coefficient based on an input operation received by the operation unit.

6. The X-ray imaging system according to claim 1 , wherein the adjustment processing unit is configured to be able to adjust the degree of suppression of bone structures so that it varies for each pixel in the generated bone-suppressed tomographic image.

7. the bone suppression processing unit is configured to perform a process of suppressing a bone structure on each of the generated X-ray images; the adjustment processing unit is configured to execute a process of adjusting a degree of suppression of bone structures for the plurality of X-ray images in which bone structures have been suppressed by the bone suppression processing unit, 2. The X-ray imaging system according to claim 1, wherein the reconstruction processing unit is configured to generate the bone-suppressed tomographic image in which the degree of suppression of the bone structure has been adjusted by executing the reconstruction processing based on the plurality of X-ray images in which the degree of suppression of the bone structure has been adjusted by the adjustment processing unit.

8. the reconstruction processing unit is configured to generate a tomographic image with bone, which is the tomographic image including a bone structure in the target region, by executing a reconstruction process on the plurality of X-ray images; the bone suppression processing unit is configured to generate the bone-suppressed tomographic image by executing a process of suppressing a bone structure on the tomographic image with bone generated by the reconstruction processing unit, The X-ray imaging system according to claim 1 , wherein the adjustment processing unit is configured to execute a process of adjusting the degree of suppression of bone structures on the bone-suppressed tomographic image generated by the bone suppression processing unit.

9. the bone suppression processing unit is configured to perform a process of suppressing a bone structure on each of the generated X-ray images; the reconstruction processing unit is configured to generate bone-present tomographic images, which are tomographic images including bone structures in the target region, by executing a reconstruction process on the plurality of X-ray images, and to generate bone-extracted tomographic images, which are tomographic images in which the bone structures in the target region are extracted, by executing a reconstruction process on a plurality of bone-extracted images, which are tomographic images in which the bone structures in the target region are extracted, generated based on the plurality of X-ray images and the plurality of X-ray images in which the bone structures are suppressed by the bone suppression processing unit; 2. The X-ray imaging system according to claim 1, wherein the adjustment processing unit is configured to generate the bone-suppressed tomographic image in which the degree of suppression of the bone structure is adjusted based on the bone-present tomographic image and the bone-extracted tomographic image.

10. the reconstruction processing unit is configured to generate a tomographic image with bone, which is the tomographic image including a bone structure in the target region, by executing a reconstruction process on the plurality of X-ray images; The X-ray imaging system according to claim 1 , further comprising a display unit that displays the bone-present tomographic image including a bone structure and the bone-suppressed tomographic image in which the bone structure is suppressed.

11. the target site includes at least one of a chest and an abdomen of the subject; The X-ray imaging system according to claim 1 , wherein the image processing unit is configured to generate the bone-suppressed tomographic image in which bone structures including ribs are suppressed in at least one of the chest and the abdomen.

12. generating a plurality of X-ray images by performing tomosynthesis imaging on a target region of a subject while moving at least one of an X-ray irradiator that irradiates the target region with X-rays and an X-ray detector that detects the X-rays irradiated from the X-ray irradiator; generating a bone-suppressed tomographic image, which is a tomographic image showing a cross section of the subject in which a bone structure in the target region is suppressed, based on the plurality of X-ray images generated by performing the tomosynthesis imaging; The step of generating the bone-suppressed tomographic image includes: a step of executing a process of suppressing bone structures in the target region using a trained model trained using teacher input images including bone structures and teacher output images in which bone structures are suppressed or removed from the teacher input images, based on the generated plurality of X-ray images; performing a reconstruction process to generate the tomographic image based on the generated plurality of X-ray images; and adjusting the degree of suppression of bone structures in the generated bone-suppressed tomographic image.

Images