Estimation device, method, and program

Abstract

To accurately predict a locomotorium disease in an estimation device, method, and program.SOLUTION: An estimation device includes at least one processor. The processor functions as a learned neural network for deriving an estimation result related to bone density of a bone part from a plain radiation image acquired by executing plain radiography of a subject including the bone part. The learned neural network is learned by using, as teacher data, (i) two radiation images acquired by imaging the subject including the bone part by radioactive rays with different energy distribution, (ii) the radiation image of the subject and a bone image showing the bone part of the subject, or (iii) the radiation image of the subject and a bone density image indicating the bone density of the bone part of the subject, and information related to the bone density of the bone part of the subject.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present disclosure relates to an estimation device, a method, and a program. [Background technology]

[0002] DXA (Dual X-ray Absorptiometry) is one of the representative bone mineral quantification methods used to diagnose bone density in bone diseases such as osteoporosis. DXA uses the attenuation coefficient μ (cm) of radiation that enters and penetrates the human body, which depends on the materials that make up the human body (e.g., bone). 2 / g) and its density ρ(g / cm 3 This method calculates bone mineral density from the pixel values ​​of radiographic images taken with two types of radiation energy, utilizing the attenuation of bone, characterized by the radiation energy (t) and thickness (cm).

[0003] Various methods for evaluating bone density using radiographic images acquired by photographing a subject have also been proposed. For example, Patent Documents 1 and 2 propose a method for estimating information related to bone density from images of bones by using a trained neural network constructed by training a neural network. In the method described in Patent Document 1, the neural network is trained using images of bones and bone density acquired by simple radiography as training data. In the method described in Patent Document 1, the neural network is trained using images of bones acquired by simple radiography, bone density, and information related to bone density (e.g., age, sex, weight, drinking habits, smoking habits, fracture history, body fat percentage, subcutaneous fat percentage, etc.) as training data.

[0004] Note that plain radiography is an imaging method in which a subject is irradiated with radiation once to obtain a single two-dimensional image that is a transmission image of the subject. In the following description, a radiographic image obtained by plain radiography will be referred to as a plain radiographic image. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] U.S. Patent No. 6,064,716 [Patent Document 2] International Publication No. 2020 / 054738 Summary of the Invention [Problem to be solved by the invention]

[0006] However, there is a demand for a more accurate estimation of bone mineral density.

[0007] The present disclosure has been made in consideration of the above circumstances, and aims to enable bone mineral density to be estimated with high accuracy. [Means for solving the problem]

[0008] An estimation device according to the present disclosure includes at least one processor, the processor functions as a trained neural network that derives an estimation result related to bone density of a bone portion from a plain radiographic image obtained by plain radiography of a subject including a bone portion; The trained neural network is trained using, as training data, (i) two radiological images obtained by photographing a subject including bones using radiation with different energy distributions, (ii) a radiological image of the subject and a bone image representing the subject's bones, or (iii) a radiological image of the subject and a bone density image representing the bone density of the subject's bones, and information related to the bone density of the subject's bones.

[0009] In the estimation device according to the present disclosure, the information related to bone density is a body thickness distribution of the subject estimated based on at least one of two radiographic images obtained by imaging the subject including bones and soft tissues with radiation having different energy distributions; The imaging conditions under which the two radiographic images were obtained, and The weighted subtraction may be derived based on pixel values ​​of a bone region in a bone image from which bones are extracted, the pixel values ​​being derived by energy subtraction processing that performs weighted subtraction between two radiation images.

[0010] In the estimation device according to the present disclosure, the bone image is generated by recognizing the bones and soft tissues of the subject using at least one of the two radiographic images; Deriving attenuation coefficients for the bones and soft tissues using the bone and soft tissue recognition results and the two radiographic images; It may be derived by performing energy subtraction processing using the attenuation coefficient.

[0011] In addition, in the estimation device according to the present disclosure, a new weighting coefficient to be used for weighted subtraction is derived based on pixel values ​​of bones included in the bone image; A new bone image is derived by performing weighted subtraction on the two radiographic images using a new weighting factor; The weighting coefficients may be derived by repeatedly deriving new weighting coefficients based on new bone images, and deriving new bone images based on new weighting coefficients.

[0012] In addition, in the estimation device according to the present disclosure, the bone image is generated by changing the attenuation coefficient for each different energy distribution for soft tissue, the soft tissue thickness, the attenuation coefficient for each different energy distribution for bone tissue, and the bone thickness from their initial values, and deriving the difference between the value of (soft tissue attenuation coefficient × soft tissue thickness + bone attenuation coefficient × bone thickness) and each pixel value of the radiographic image for each different energy distribution; Deriving soft tissue attenuation coefficients and bone attenuation coefficients for different energy distributions that have a minimum difference or a difference that is less than a predetermined threshold; The weighting coefficient may be derived by performing an energy subtraction process using a weighting coefficient derived based on the attenuation coefficient of soft tissue and the attenuation coefficient of bone.

[0013] In addition, in the estimation device according to the present disclosure, the bone image is obtained by deriving the composition ratios of multiple components contained in the soft tissue of the subject, Deriving attenuation coefficients for different energy distributions in soft tissue for each pixel of the two radiographic images according to the composition ratio; The attenuation coefficient may be derived by performing an energy subtraction process using a weighting coefficient derived based on the derived soft tissue attenuation coefficient and a predetermined bone attenuation coefficient.

[0014] In addition, in the estimation device according to the present disclosure, the composition ratio is calculated by deriving the body thickness of the subject as a first body thickness and a second body thickness for each pixel in each of the two radiographic images, It may be derived for each pixel of the radiographic image based on the first body thickness and the second body thickness.

[0015] In addition, in the estimation device according to the present disclosure, the composition ratio is calculated by deriving a first body thickness and a second body thickness based on an attenuation coefficient for each different energy distribution for each of a plurality of compositions; The first body thickness and the second body thickness may be derived while changing the thickness of the composition and the attenuation coefficient for each composition, and may be derived based on the thickness of the composition at which the difference between the first body thickness and the second body thickness is equal to or less than a predetermined threshold value.

[0016] Furthermore, in the estimation device according to the present disclosure, the bone images may be derived by performing a scattered ray removal process to remove scattered ray components scattered by the subject from the radiation irradiated to the subject from the two radiographic images, and then performing an energy subtraction process on the two radiographic images from which the scattered ray components have been removed.

[0017] In the estimation device according to the present disclosure, the scattered radiation removal process includes acquiring radiation characteristics according to the body thickness distribution of an object interposed between the subject and a radiation detector that detects a radiological image; Deriving the primary ray distribution and the scattered ray distribution of the radiation contained in each of the two radiographic images using the imaging conditions, the body thickness distribution, and the radiation characteristics of the object; deriving an error between the sum of the primary ray distribution and the scattered ray distribution for each of the two radiographic images and the pixel value at each position of the two radiographic images, updating the body thickness distribution so that the error is less than a predetermined threshold, and repeatedly deriving radiation characteristics based on the updated body thickness distribution and deriving the primary ray distribution and the scattered ray distribution contained in each of the two radiographic images; This may be performed by subtracting the scattered radiation distribution when the error is less than a predetermined threshold value from each of the two radiographic images.

[0018] In the estimation device according to the present disclosure, the scattered radiation removal process includes deriving a first primary ray distribution and a scattered ray distribution of radiation that has passed through the subject using two radiographic images; deriving a second primary ray distribution and a scattered ray distribution of the radiation that has passed through the object using the first primary ray distribution and the scattered ray distribution, and radiation characteristics of an object that is interposed between the subject and a radiation detector that detects a radiation image; This may be performed by deriving a radiation image after transmission through the subject and object using the second primary ray distribution and the scattered ray distribution.

[0019] In addition, in the estimation device according to the present disclosure, the scattered radiation removal process derives a region detection image by detecting, in two radiographic images, a subject region where radiation has passed through the subject and reached the radiation detection unit, and a direct radiation region where radiation has directly reached the radiation detection unit without passing through the subject; deriving a scattered ray image relating to the scattered ray component based on the region detection image and scattered ray spread information relating to the spread of scattered rays; This may be done by subtracting the scattered radiation image from the two radiographic images.

[0020] In addition, in the estimation device according to the present disclosure, the bone image is obtained by deriving processing details of a first graininess reduction process for a first radiographic image having a higher S / N ratio of the two radiographic images; deriving processing details of a second graininess reduction process for a second radiographic image having a low S / N ratio based on processing details of the first graininess reduction process; performing graininess reduction processing on the first radiographic image based on the processing content of the first graininess reduction processing; performing graininess reduction processing on the second radiographic image based on the processing content of the second graininess reduction processing; It may be derived using two radiation images that have been subjected to graininess suppression processing.

[0021] In this case, the processing content of the first graininess reduction processing may be derived based on a physical quantity map of the subject derived based on at least one of the first radiographic image and the second radiographic image.

[0022] In addition, in the estimation device according to the present disclosure, the information related to bone density may include at least one of bone density, an evaluation value of the subject's fracture risk, and information indicating the healing state of the bone after treatment.

[0023] The estimation method according to the present disclosure is a method for deriving an estimation result related to bone density from a simple radiographic image using a trained neural network that derives an estimation result related to bone density of a bone portion from a simple radiographic image acquired by simply photographing a subject including a bone portion, the method comprising: The trained neural network is trained using, as training data, (i) two radiological images obtained by photographing a subject including bones using radiation with different energy distributions, (ii) a radiological image of the subject and a bone image representing the subject's bones, or (iii) a radiological image of the subject and a bone density image representing the bone density of the subject's bones, and information related to the bone density of the subject's bones.

[0024] The estimation method according to the present disclosure may be provided as a program for causing a computer to execute the method. [Effects of the Invention]

[0025] According to the present disclosure, bone density can be estimated with high accuracy. [Brief explanation of the drawings]

[0026] [Figure 1] FIG. 1 is a schematic block diagram showing the configuration of a radiographic imaging system to which an estimation device according to a first embodiment of the present disclosure is applied. [Figure 2] FIG. 1 is a diagram showing a schematic configuration of an estimation device according to a first embodiment. [Figure 3] FIG. 1 is a diagram showing a functional configuration of an estimation device according to a first embodiment. [Figure 4] FIG. 1 is a diagram showing a schematic configuration of a neural network used in this embodiment. [Figure 5] Diagram showing training data [Figure 6] FIG. 1 is a diagram showing a schematic configuration of an information derivation device according to a first embodiment; [Figure 7] FIG. 1 is a diagram showing a functional configuration of an information derivation device according to a first embodiment; [Figure 8] Figure showing bone images [Figure 9] A diagram showing the relationship between contrast between bones and soft tissues and the subject's body thickness. [Figure 10] FIG. 10 is a diagram showing an example of a lookup table for obtaining a correction coefficient; [Figure 11] Diagram to explain neural network learning [Figure 12] Conceptual diagram of the processing performed by a trained neural network [Figure 13] Figure showing the display screen of the estimation results [Figure 14] 1 is a flowchart of a learning process performed in the first embodiment. [Figure 15] 1 is a flowchart of an estimation process performed in the first embodiment. [Figure 16] FIG. 10 is a diagram showing a functional configuration of an information derivation device according to a second embodiment. [Figure 17] FIG. 10 is a diagram for explaining calculation of an index value representing attenuation. [Figure 18] FIG. 10 is a diagram for explaining calculation of an index value representing attenuation. [Figure 19] FIG. 10 is a diagram showing a functional configuration of an information derivation device according to a third embodiment. [Figure 20]A table defining the relationship between body thickness distribution and initial weighting coefficients. [Figure 21] FIG. 10 is a diagram showing a table defining the relationship between pixel values ​​of bones and thicknesses of bones. [Figure 22] FIG. 1 is a table defining the relationship between the thickness of soft tissue and bone tissue and the weighting coefficient. [Figure 23] FIG. 10 is a diagram showing a functional configuration of an information derivation device according to a fourth embodiment. [Figure 24] FIG. 10 is a table defining the relationship between the initial value of the thickness of the soft part and the initial value of the attenuation coefficient of the soft part. [Figure 25] A table defining the relationship between the thickness of soft tissue and bone and the attenuation coefficient. [Figure 26] FIG. 10 is a diagram showing a functional configuration of an information derivation device according to a fifth embodiment. [Figure 27] FIG. 1 is a diagram for explaining the difference in body thickness derived from low-energy images and high-energy images. [Figure 28] A table showing the relationship between the difference in body thickness derived from two radiographic images and the composition ratio of fat. [Figure 29] FIG. 13 is a diagram showing the functional configuration of a scattered radiation removal unit in the information derivation device according to the sixth embodiment. [Figure 30] FIG. 13 is a diagram for explaining photography in the sixth embodiment. [Figure 31] FIG. 1 is a diagram for explaining measurement of scattered ray transmittance according to the subject's body thickness. [Figure 32] FIG. 1 is a diagram for explaining measurement of scattered ray transmittance according to the subject's body thickness. [Figure 33] A table showing the relationship between the subject's body thickness distribution and the scattered ray transmittance of objects interposed between the subject and the radiation detector. [Figure 34] A diagram for explaining measurement of primary ray transmittance according to the subject's body thickness. [Figure 35] A diagram for explaining measurement of primary ray transmittance according to the subject's body thickness. [Figure 36] A table showing the relationship between the subject's body thickness distribution and the primary ray transmittance of objects interposed between the subject and the radiation detector. [Figure 37] A diagram showing the state where an air gap exists between the top plate and the grid [Figure 38] FIG. 13 is a diagram showing the functional configuration of a scattered radiation removal unit in an information derivation device according to a seventh embodiment. [Figure 39] FIG. 13 is a diagram for explaining the function of a first lead-out section in the seventh embodiment. [Figure 40] A diagram for explaining a method for estimating the body thickness of a subject. [Figure 41] Diagram showing the point spread function [Figure 42] Diagram showing the path of radiation [Figure 43] FIG. 13 is a diagram showing a functional configuration of an information derivation device according to an eighth embodiment. [Figure 44] FIG. 10 is a diagram showing a bilateral filter for a first radiation image. [Figure 45] FIG. 45 is a diagram showing a local region of a second radiographic image corresponding to the local region of the first radiographic image shown in FIG. 44; [Figure 46] FIG. 10 is a diagram showing an example of a bilateral filter for a second radiation image; [Figure 47] FIG. 13 is a diagram showing a functional configuration of an information derivation device according to a ninth embodiment. [Figure 48] An example of a bilateral filter for a physical quantity map. [Figure 49] FIG. 23 is a diagram showing a functional configuration of an information derivation device according to a tenth embodiment. [Figure 50] FIG. 10 shows an example of the energy spectrum of radiation after passing through muscle tissue and fat tissue. [Figure 51] Graph showing the relationship between statistical values ​​and the probability of fracture occurrence within 10 years [Figure 52] Another example of training data [Figure 53] FIG. 23 is a diagram showing a functional configuration of an information derivation device according to an eleventh embodiment. [Figure 54] A diagram showing an example of an artificial bone embedded in the bone of a subject. [Figure 55] Graph showing an example of the relationship between the distance from the stem inside the femur and the bone mineral content at each stage after surgery. [Figure 56] A cross-sectional view showing an example of the cross-sectional structure of a human bone [Figure 57] Another example of training data [Figure 58] FIG. 23 is a diagram showing the functional configuration of a scattered radiation removal unit in the information derivation device according to the twelfth embodiment. [Figure 59] FIG. 1 is a diagram illustrating detection of a subject region and a direct radiation region. [Figure 60] FIG. 10 is a diagram showing an area detection image of a specific line portion. [Figure 61] A diagram showing a scattered radiation image of a specific line portion [Figure 62] Diagram showing the body thickness distribution in specific line areas [Figure 63] Another example of training data [Figure 64] Another example of training data [Figure 65] FIG. 10 is a diagram showing another example of the display screen for the estimation results. DETAILED DESCRIPTION OF THE INVENTION

[0027] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. Fig. 1 is a schematic block diagram showing the configuration of a radiographic image capturing system to which an estimation device according to a first embodiment of the present disclosure is applied. As shown in Fig. 1, the radiographic image capturing system according to the first embodiment includes an imaging device 1, an image storage system 9, an estimation device 10 according to the first embodiment, and an information derivation device 50. The imaging device 1, the estimation device 10, and the information derivation device 50 are connected to the image storage system 9 via a network (not shown).

[0028] The imaging device 1 is capable of performing energy subtraction by a so-called one-shot method in which radiation such as X-rays emitted from a radiation source 3 and transmitted through a subject H is irradiated at different energies onto a first radiation detector 5 and a second radiation detector 6. During imaging, as shown in Fig. 1, the first radiation detector 5, a radiation energy converting filter 7 made of a copper plate or the like, and the second radiation detector 6 are arranged in this order from the side closest to the radiation source 3, and the radiation source 3 is driven. The first and second radiation detectors 5 and 6 are in close contact with the radiation energy converting filter 7.

[0029] As a result, the first radiation detector 5 acquires a first radiographic image G1 of the subject H using low-energy radiation that also includes so-called soft rays. The second radiation detector 6 acquires a second radiographic image G2 of the subject H using high-energy radiation from which soft rays have been removed. Therefore, the first radiographic image G1 and the second radiographic image G2 are acquired by capturing images of the subject H using radiation with different energy distributions. The first and second radiographic images G1, G2 are input to the estimation device 10. Both the first radiographic image G1 and the second radiographic image G1 are front images that include the area around the crotch of the subject H.

[0030] The first and second radiation detectors 5, 6 are capable of repeatedly recording and reading out radiation images, and may be so-called direct type radiation detectors that generate electric charges upon direct exposure to radiation, or so-called indirect type radiation detectors that convert radiation into visible light and then convert the visible light into electric charge signals. The radiation image signal readout method is preferably a TFT readout method in which the radiation image signal is read out by turning a TFT (thin film transistor) switch on and off, or an optical readout method in which the radiation image signal is read out by irradiating the detector with readout light, but is not limited to these, and other methods may also be used.

[0031] The imaging device 1 can also acquire a simple radiographic image G0, which is a simple two-dimensional image of the subject H, by performing simple radiography of the subject H using only the first radiation detector 5. The imaging to acquire the first and second radiographic images G1, G2 is referred to as energy subtraction imaging to distinguish it from simple radiography. In this embodiment, the first and second radiographic images G1, G2 acquired by energy subtraction imaging are used as learning data, which will be described later. Furthermore, the simple radiographic image G0 acquired by simple radiography is used to derive estimation results related to bone density, as will be described later.

[0032] The image storage system 9 is a system that stores image data of radiographic images acquired by the imaging device 1. The image storage system 9 extracts an image from the stored radiographic images in response to a request from the estimation device 10 and transmits it to the device that has issued the request. A specific example of the image storage system 9 is a PACS (Picture Archiving and Communication Systems). In this embodiment, the image storage system 9 stores a large amount of training data for training a neural network, which will be described later.

[0033] Next, an estimation device according to a first embodiment will be described. First, with reference to FIG. 2, the hardware configuration of the estimation device according to the first embodiment will be described. As shown in FIG. 2, the estimation device 10 is a computer such as a workstation, a server computer, or a personal computer, and includes a CPU (Central Processing Unit) 11, non-volatile storage 13, and memory 16 as a temporary storage area. The estimation device 10 also includes a display 14 such as a liquid crystal display, an input device 15 such as a keyboard and a mouse, and a network I / F (Interface) 17 connected to a network (not shown). The CPU 11, the storage 13, the display 14, the input device 15, the memory 16, and the network I / F 17 are connected to a bus 18. The CPU 11 is an example of a processor in the present disclosure.

[0034] The storage 13 is realized by a hard disk drive (HDD), a solid state drive (SSD), a flash memory, etc. The storage 13 as a storage medium stores the estimation program 12A and the learning program 12B installed in the estimation device 10. The CPU 11 reads out the estimation program 12A and the learning program 12B from the storage 13, expands them in the memory 16, and executes the expanded estimation program 12A and the learning program 12B.

[0035] The estimation program 12A and the learning program 12B are stored in a state accessible from the outside in a storage device of a server computer connected to a network or in a network storage, and are downloaded and installed in response to a request into a computer constituting the estimation device 10. Alternatively, they are recorded on a recording medium such as a DVD (Digital Versatile Disc) or a CD-ROM (Compact Disc Read Only Memory) and distributed, and are installed from the recording medium into a computer constituting the estimation device 10.

[0036] Next, the functional configuration of the estimation device according to the first embodiment will be described. Fig. 3 is a diagram showing the functional configuration of the estimation device according to the first embodiment. As shown in Fig. 3, the estimation device 10 includes an image acquisition unit 21, an information acquisition unit 22, an estimation unit 23, a learning unit 24, and a display control unit 25. The CPU 11 executes an estimation program 12A to function as the image acquisition unit 21, the information acquisition unit 22, the estimation unit 23, and the display control unit 25. The CPU 11 executes a learning program 12B to function as the learning unit 24.

[0037] The image acquisition unit 21 causes the imaging device 1 to perform energy subtraction imaging of the subject H, thereby acquiring a first radiographic image G1 and a second radiographic image G2, which are, for example, frontal images of the area around the crotch of the subject H, from the first and second radiation detectors 5, 6. When acquiring the first radiographic image G1 and the second radiographic image G2, imaging conditions such as the imaging dose, radiation quality, tube voltage, SID (Source Image Receptor Distance) which is the distance between the radiation source 3 and the surfaces of the first and second radiation detectors 5, 6, SOD (Source Object Distance) which is the distance between the radiation source 3 and the surface of the subject H, and the presence or absence of an anti-scatter grid are set.

[0038] The SOD and SID are used to calculate the body thickness distribution as described below. The SOD is preferably obtained using, for example, a TOF (Time of Flight) camera. The SID is preferably obtained using, for example, a potentiometer, an ultrasonic range finder, or a laser range finder.

[0039] The imaging conditions may be set by the operator through input device 15. The set imaging conditions are stored in storage 13. The first and second radiographic images G1, G2 acquired by energy subtraction imaging and the imaging conditions are also transmitted to and stored in image storage system 9. The first and second radiographic images G1, G2 are used to derive training data, which will be described later.

[0040] The image acquisition unit 21 also acquires a simple radiographic image G0, which is a front image of the crotch area of ​​the subject H, by causing the imaging device 1 to perform simple imaging of the subject H using only the first radiation detector 5.

[0041] In this embodiment, the first and second radiographic images G1, G2 and the simple radiographic image G0 may be acquired by a program separate from the estimation program 12A and stored in the storage 13. In this case, the image acquisition unit 21 acquires the first and second radiographic images G1, G2 and the simple radiographic image G0 stored in the storage 13 by reading them out from the storage 13 for processing.

[0042] The information acquisition unit 22 acquires training data for training a neural network, which will be described later, from the image storage system 9 via the network I / F 17.

[0043] The estimation unit 23 derives an estimation result related to the bone density of the bone portion included in the subject H from the simple radiographic image G0. In this embodiment, the estimation result related to the bone density is an estimation result of the bone density of the target bone in the bone portion region included in the simple radiographic image G0. To this end, the estimation unit 23 derives the estimation result related to the bone density using a trained neural network 23A that outputs bone density when the simple radiographic image G0 is input.

[0044] The learning unit 24 constructs a trained neural network 23A by machine learning a neural network using training data. Examples of neural networks include a simple perceptron, a multilayer perceptron, a deep neural network, a convolutional neural network, a deep belief network, a recurrent neural network, and a probabilistic neural network. In this embodiment, a convolutional neural network is used as the neural network.

[0045] Fig. 4 is a diagram showing a neural network used in this embodiment. As shown in Fig. 4, the neural network 30 includes an input layer 31, an intermediate layer 32, and an output layer 33. The intermediate layer 32 includes, for example, a plurality of convolutional layers 35, a plurality of pooling layers 36, and a fully connected layer 37. In the neural network 30, the fully connected layer 37 is located before the output layer 33. In the neural network 30, the convolutional layers 35 and the pooling layers 36 are alternately arranged between the input layer 31 and the fully connected layer 37.

[0046] The configuration of the neural network 30 is not limited to the example shown in Fig. 4. For example, the neural network 30 may include one convolutional layer 35 and one pooling layer 36 between the input layer 31 and the fully connected layer 37.

[0047] Fig. 5 is a diagram showing an example of training data used for training a neural network. As shown in Fig. 5, training data 40 consists of training data 41 and correct answer data 42. In this embodiment, the data input to trained neural network 23A to obtain a bone mineral density estimation result is a simple radiographic image G0, while training data 41 includes two radiographic images, a first radiographic image G1 and a second radiographic image G2, acquired by the above-mentioned energy subtraction imaging.

[0048] The correct answer data 42 is the bone density of the target bone (i.e., femur) of the subject from which the learning data 41 was obtained. In this embodiment, the bone density per unit area is estimated from the two-dimensional plain radiographic image G0, so the unit of bone density is (g / cm 2 ) The bone density, which is the correct answer data 42, is derived by the information derivation device 50. In this embodiment, the bone density, which is the correct answer data 42, is derived by using, for example, the method described in Japanese Patent Application Laid-Open No. 2019-202035. Note that the bone density, which is the correct answer data 42, is an example of information related to the bone density of the bones of the subject. The information derivation device 50 will be described below.

[0049] Fig. 6 is a schematic block diagram showing the configuration of an information derivation device according to a first embodiment. As shown in Fig. 6, information derivation device 50 according to the first embodiment is a computer such as a workstation, a server computer, or a personal computer, and includes a CPU 51, non-volatile storage 53, and memory 56 as a temporary storage area. Information derivation device 50 also includes a display 54 such as a liquid crystal display, an input device 55 including a keyboard, a pointing device such as a mouse, and a network I / F 57 connected to a network (not shown). CPU 51, storage 53, display 54, input device 55, memory 56, and network I / F 57 are connected to a bus 58.

[0050] The storage 53 is realized by an HDD, an SSD, a flash memory, or the like, similar to the storage 13. The storage 53 as a storage medium stores an information derivation program 52. The CPU 51 reads the information derivation program 52 from the storage 53, expands it in the memory 56, and executes the expanded information derivation program 52.

[0051] Next, the functional configuration of the information derivation device according to the first embodiment will be described. Fig. 7 is a diagram showing the functional configuration of the information derivation device according to the first embodiment. As shown in Fig. 7, the information derivation device 50 according to the first embodiment includes an image acquisition unit 61, a scattered radiation removal unit 62, a subtraction unit 63, and a bone density derivation unit 64. When the CPU 51 executes the information derivation program 52, the CPU 51 functions as the image acquisition unit 61, the scattered radiation removal unit 62, the subtraction unit 63, and the bone density derivation unit 64.

[0052] The image acquisition unit 61 acquires the first radiographic image G1 and the second radiographic image G2, which become the learning data 41 stored in the image storage system 9. Note that the image acquisition unit 61 may acquire the first radiographic image G1 and the second radiographic image G2 by causing the imaging device 1 to capture an image of the subject H, similar to the image acquisition unit 21 of the estimation device 10.

[0053] The image acquisition unit 61 also acquires the imaging conditions used when the first and second radiographic images were acquired and stored in the image storage system 9. The imaging conditions include the imaging dose, tube voltage, SID, SOD, and the presence or absence of an anti-scatter grid when the first radiographic image G1 and the second radiographic image G2 were acquired.

[0054] Here, each of the first radiographic image G1 and the second radiographic image G2 contains scattered ray components based on radiation scattered within the subject H in addition to primary ray components of radiation that have passed through the subject H. For this reason, the scattered ray removal unit 62 removes the scattered ray components from the first radiographic image G1 and the second radiographic image G2. For example, the scattered ray removal unit 62 may remove the scattered ray components from the first radiographic image G1 and the second radiographic image G2 by applying the method described in Japanese Patent Application Laid-Open No. 2015-043959. When using the method described in Japanese Patent Application Laid-Open No. 2015-043959, the body thickness distribution of the subject H and the scattered ray components for removing the scattered ray components are simultaneously derived.

[0055] The following describes the removal of scattered radiation components from the first radiographic image G1, but the removal of scattered radiation components from the second radiographic image G2 can also be performed in a similar manner. First, the scattered radiation removal unit 62 acquires a virtual model of the subject H having an initial body thickness distribution T0(x,y). The virtual model is data virtually representing the subject H, in which the body thickness according to the initial body thickness distribution T0(x,y) is associated with the coordinate position of each pixel in the first radiographic image G1. The virtual model of the subject H having the initial body thickness distribution T0(x,y) may be pre-stored in the storage 53 of the information derivation device 50. The scattered radiation removal unit 62 may also calculate the body thickness distribution T(x,y) of the subject H based on the SID and SOD included in the imaging conditions. In this case, the initial body thickness distribution T0(x,y) can be obtained by subtracting the SOD from the SID.

[0056] Next, the scattered radiation removal unit 62 generates an estimated image based on the virtual model by combining an estimated primary radiation image obtained by estimating the primary radiation image obtained by photographing the virtual model and an estimated scattered radiation image obtained by estimating the scattered radiation image obtained by photographing the virtual model, as an estimated image based on the first radiation image G1 obtained by photographing the subject H.

[0057] Next, the scattered radiation removal unit 62 corrects the initial body thickness distribution T0(x,y) of the virtual model so as to reduce the difference between the estimated image and the first radiographic image G1. The scattered radiation removal unit 62 repeatedly generates the estimated image and corrects the body thickness distribution until the difference between the estimated image and the first radiographic image G1 satisfies a predetermined termination condition. The scattered radiation removal unit 62 derives the body thickness distribution when the termination condition is satisfied as the body thickness distribution T(x,y) of the subject H. Furthermore, the scattered radiation removal unit 62 removes the scattered radiation components contained in the first radiographic image G1 by subtracting the scattered radiation components when the termination condition is satisfied from the first radiographic image G1.

[0058] The subtraction unit 63 performs energy subtraction processing to derive a bone image Gb from the first and second radiographic images G1, G2, from which the bones of the subject H have been extracted. Note that the first and second radiographic images G1, G2 in the subsequent processing have had scattered radiation components removed. When deriving the bone image Gb, the subtraction unit 63 performs weighted subtraction between corresponding pixels in the first and second radiographic images G1, G2, as shown in the following equation (1), to generate a bone image Gb from which the bones of the subject H contained in each of the radiographic images G1, G2 have been extracted, as shown in FIG. 8. In equation (1), α is a weighting coefficient. Note that the pixel value of each pixel in the bone region of the bone image Gb is the bone pixel value. Gb(x,y)=α·G2(x,y)-G1(x,y) (1)

[0059] The bone density deriving unit 64 derives bone density for each pixel of the bone image Gb. In this embodiment, the bone density deriving unit 64 derives bone density B by converting each pixel value of the bone image Gb into the pixel value of a bone image acquired under standard imaging conditions. Specifically, the bone density deriving unit 64 derives bone density by correcting each pixel value of the bone image Gb using a correction coefficient acquired from a lookup table described below.

[0060] Here, the higher the tube voltage of the radiation source 3 and the higher the energy of the radiation emitted from the radiation source 3, the smaller the contrast between soft tissue and bone in the radiographic image. Furthermore, as the radiation passes through the subject H, low-energy components of the radiation are absorbed by the subject H, causing beam hardening, which increases the energy of the radiation. The increase in the energy of the radiation due to beam hardening becomes greater as the body thickness of the subject H increases.

[0061] FIG. 9 is a diagram showing the relationship between the contrast between bones and soft tissues and the body thickness of subject H. FIG. 9 shows the relationship between the contrast between bones and soft tissues and the body thickness of subject H at three tube voltages: 80 kV, 90 kV, and 100 kV. As shown in FIG. 9, the higher the tube voltage, the lower the contrast. Furthermore, once the body thickness of subject H exceeds a certain value, the greater the body thickness, the lower the contrast. Note that the greater the pixel value of the bone region in bone image Gb, the greater the contrast between bones and soft tissues. Therefore, the relationship shown in FIG. 9 shifts toward higher contrast as the pixel value of the bone region in bone image Gb increases.

[0062] In the first embodiment, a lookup table for acquiring correction coefficients for correcting differences in contrast in the bone image Gb depending on the tube voltage at the time of imaging and reduction in contrast due to the influence of beam hardening is stored in the storage 53 of the information derivation device 50. The correction coefficients are coefficients for correcting each pixel value of the bone image Gb.

[0063] FIG. 10 is a diagram showing an example of a lookup table for acquiring correction coefficients. FIG. 10 illustrates a lookup table (hereinafter simply referred to as a table) LUT1 in which the reference imaging condition is set to a tube voltage of 90 kV. As shown in FIG. 10, in table LUT1, the higher the tube voltage and the greater the body thickness of the subject H, the larger the correction coefficient set. In the example shown in FIG. 10, since the reference imaging condition is a tube voltage of 90 kV, the correction coefficient is 1 when the tube voltage is 90 kV and the body thickness is 0. Note that although table LUT1 is shown two-dimensionally in FIG. 10, the correction coefficient differs depending on the pixel values ​​of the bone region. Therefore, table LUT1 is actually a three-dimensional table with an axis representing the pixel values ​​of the bone region added.

[0064] The bone density deriving unit 64 extracts, from the table LUT1, a correction coefficient C0(x, y) for each pixel according to the imaging conditions including the body thickness distribution T(x, y) of the subject H and the set value of the tube voltage stored in the storage 13. Then, as shown in the following formula (2), the bone density deriving unit 64 multiplies each pixel (x, y) of the bone region in the bone image Gb by the correction coefficient C0(x, y) to obtain the bone density B(x, y) (g / cm) for each pixel of the bone image Gb. 2 ) is derived The bone density B(x, y) derived in this manner represents the pixel values ​​of the bone region included in the radiographic image obtained by imaging the subject H under the standard imaging condition of a tube voltage of 90 kV, from which the effects of beam hardening have been removed. Therefore, the bone density derivation unit 64 derives a bone density image in which the derived bone density is the pixel value of each pixel. B(x,y)=C0(x,y)×Gb(x,y) (2)

[0065] Furthermore, in this embodiment, the bone density deriving unit 64 derives a representative value of bone density B only for the target bone. For example, if the target bone is the femur, the bone density deriving unit 64 derives a representative value of bone density B for the femur region by deriving a representative value of bone density B for each pixel in the femur region in the bone image Gb. The representative value may be an average value, a median value, a minimum value, a maximum value, or the like. In this embodiment, the representative value of bone density of the femur, which is the target bone, is used as the correct answer data 42.

[0066] The bone density used as the correct answer data 42 is derived at the same time as the learning data 41 is acquired and transmitted to the image storage system 9. In the image storage system 9, the learning data 41 and the correct answer data 42 are associated with each other and stored as training data 40. To improve the robustness of learning, additional training data 40 may be created and stored, including images obtained by performing at least one of the following on the same image: enlargement / reduction, contrast change, translation, in-plane rotation, inversion, and noise addition.

[0067] Returning to the estimation device 10, the learning unit 24 trains the neural network using a large amount of training data 40. FIG. 11 is a diagram for explaining the training of the neural network 30. When training the neural network 30, the learning unit 24 inputs training data 41, i.e., the first and second radiographic images G1 and G2, to the input layer 31 of the neural network 30. The learning unit 24 then causes the output layer 33 of the neural network 30 to output the bone mineral density of the target bone as output data 47. The learning unit 24 then derives the difference between the output data 47 and the ground truth data 42 as the loss L0.

[0068] The learning unit 24 trains the neural network 30 based on the loss L0. Specifically, the learning unit 24 adjusts the kernel coefficients in the convolutional layer 35, the connection weights between layers, the connection weights in the fully connected layer 37, and the like (hereinafter referred to as parameters 48) so as to reduce the loss L0. The parameters 48 can be adjusted, for example, by backpropagation. The learning unit 24 repeatedly adjusts the parameters 48 until the loss L0 becomes equal to or less than a predetermined threshold. In this way, when a plain radiographic image G0 is input, the parameters 48 are adjusted so as to output the bone mineral density of the target bone, and a trained neural network 23A is constructed. The constructed trained neural network 23A is stored in the storage 13.

[0069] Fig. 12 is a conceptual diagram of the processing performed by the trained neural network 23A. As shown in Fig. 12, when a plain radiographic image G0 of a patient is input to the trained neural network 23A constructed as described above, the trained neural network 23A outputs the bone density of the target bone (i.e., the femur) included in the input plain radiographic image G0.

[0070] The display control unit 25 displays the bone density estimation results estimated by the estimation unit 23 on the display 14. FIG. 13 is a diagram showing a display screen for the estimation results. As shown in FIG. 13, a display screen 70 has an image display area 71 and a bone density display area 72. A plain radiographic image G0 of the subject H is displayed in the image display area 71. Furthermore, a representative value of the bone density around the femoral joint, based on the bone density estimated by the estimation unit 23, is displayed in the bone density display area 72.

[0071] Next, the processing performed in the first embodiment will be described. FIG. 14 is a flowchart showing the learning processing performed in the first embodiment. First, the information acquisition unit 22 acquires training data 40 from the image storage system 9 (step ST1). The learning unit 24 inputs training data 41 included in the training data 40 into the neural network 30 to output bone mineral density, and trains the neural network 30 using a loss L0 based on the difference from the ground truth data 42 (step ST2), and returns to step ST1. The learning unit 24 then repeats the processing in steps ST1 and ST2 until the loss L0 reaches a predetermined threshold value, and ends the learning processing. Note that the learning unit 24 may end the learning processing by repeating the learning a predetermined number of times. In this way, the learning unit 24 constructs a trained neural network 23A.

[0072] Next, the estimation process in the first embodiment will be described. Fig. 15 is a flowchart showing the estimation process in the first embodiment. It is assumed that the simple radiographic image G0 is acquired by radiography and stored in the storage 13. When an instruction to start the process is input from the input device 15, the image acquisition unit 21 acquires the simple radiographic image G0 from the storage 13 (step ST11). Next, the estimation unit 23 derives an estimation result related to bone density from the simple radiographic image G0 (step ST12). Then, the display control unit 25 displays the estimation result related to bone density derived by the estimation unit 23 on the display 14 together with the simple radiographic image G0 (step ST13), and the process ends.

[0073] As described above, in this embodiment, an estimation result related to the bone density of the subject H included in the simple radiographic image G0 is derived using a trained neural network 23A constructed by training using the first and second radiographic images G1 and G2 as training data. Here, in this embodiment, two radiographic images, the first and second radiographic images G1 and G2, are used for training the neural network. Therefore, compared to a case where one radiographic image and information related to bone density are used as training data, the trained neural network 23A can derive an estimation result related to bone density from the simple radiographic image G0 with greater accuracy. Therefore, according to this embodiment, an estimation result related to bone density can be derived with greater accuracy.

[0074] In the first embodiment, a value measured by DXA or ultrasound may be used as the bone density of the correct answer data 42. In a device that measures bone density using ultrasound, for example, ultrasound is applied to the lower back to measure the bone density of the lower back, or ultrasound is applied to the heel to measure the bone density of the heel.

[0075] In the first embodiment, when deriving the bone density of the correct answer data 42, the bones and soft tissues of the subject H may be recognized using at least one of the first and second radiographic images G1 and G2, and the bone and soft tissue recognition results and the first and second radiographic images G1 and G2 may be used to derive radiation attenuation coefficients for the bones and soft tissues. Energy subtraction processing may then be performed using the derived attenuation coefficients to derive the bone image Gb. This will be described below as a second embodiment. The energy subtraction processing in the second embodiment is described, for example, in International Publication No. WO 2020 / 175319.

[0076] Fig. 16 is a diagram showing the functional configuration of an information derivation device according to the second embodiment. In Fig. 16, the same components as those in Fig. 7 are given the same reference numerals, and detailed descriptions thereof will be omitted. As shown in Fig. 16, an information derivation device 50A according to the second embodiment further includes a structure recognition unit 65 and a weighting coefficient derivation unit 66 in addition to the components of the information derivation device 50 according to the first embodiment.

[0077] The structure recognition unit 65 recognizes structures included in the subject H using at least one of the first and second radiographic images G1, G2. In the second embodiment, the structures to be recognized are bones and soft tissue. In the second embodiment, the structure recognition unit 65 uses both the first and second radiographic images G1, G2 acquired by the image acquisition unit 61 for recognition processing; however, the structure recognition unit 65 may use either the first or second radiographic images G1, G2 for recognition processing. Note that the structure recognition unit 65 may recognize structures using the first and second radiographic images G1, G2 after the scattered radiation removal processing, or may recognize structures using the first and second radiographic images G1, G2 before the scattered radiation removal processing.

[0078] The structure recognition unit 65 recognizes the position, size, and / or shape, etc. of structures included in the subject H captured in the first and second radiographic images G1 and G2. That is, the recognition process performed by the structure recognition unit 65 is a process for identifying the position, size, and / or shape, etc. of structures that have boundaries with other tissues, etc., in the subject H captured in the radiographic images. In the second embodiment, the bones and soft tissues of the subject H are recognized as structures.

[0079] The weighting coefficient derivation unit 66 uses the recognition result of the structure recognition unit 65 and the first and second radiographic images G1, G2 to derive an index value representing the attenuation of radiation for the structure recognized by the structure recognition unit 65 as a weighting coefficient α to be used in subtraction processing. The attenuation coefficient is a so-called radiation source attenuation coefficient, and represents the degree (proportion) of attenuation of radiation due to absorption, scattering, etc. The attenuation coefficient varies depending on the specific composition (density, etc.) and thickness (mass) of the structure through which radiation passes.

[0080] The weighting coefficient derivation unit 66 calculates an index value representing attenuation using the ratio or difference between pixel values ​​of corresponding pixels in the first and second radiographic images G1 and G2. FIGS. 17 and 18 are diagrams for explaining the calculation of index values ​​representing attenuation. Note that FIGS. 17 and 18 illustrate the calculation of index values ​​representing attenuation for three structures. As shown in FIG. 17, assume that the first radiographic image G1 contains three types of structures with compositions "Ca," "Cb," and "Cc," and that the pixel values ​​of these structures in the first radiographic image G1 are all "V1." Meanwhile, the pixel values ​​of corresponding pixels in the second radiographic image G2 are "Va," "Vb," and "Vc," respectively. The degree of decrease in pixel value corresponds to the degree of attenuation of radiation by each structure (each composition). 18, the weighting coefficient derivation unit 66 can calculate an index value μa representing the attenuation of structures with a composition "Ca," an index value μb representing the attenuation of structures with a composition "Cb," and an index value μc representing the attenuation of structures with a composition "Cc" by using the ratio or difference between the pixel value of the first radiographic image G1 and the corresponding pixel value of the second radiographic image G2. In the second embodiment, the weighting coefficient derivation unit 66 calculates an index value representing the attenuation of bone and an index value representing the attenuation of soft tissue by defining the compositions as bone and soft tissue.

[0081] Note that the index value μ representing attenuation can be calculated by knowing the ratio or difference between the pixel values ​​in the first radiographic image G1 and the pixel values ​​of the corresponding pixels in the second radiographic image G2. For the sake of explanation, the pixel values ​​of the compositions "Ca," "Cb," and "Cc" are set to a common value "V1" in the first radiographic image G1, but the pixel values ​​of the compositions "Ca," "Cb," and "Cc" do not need to be common in the first radiographic image G1.

[0082] In this embodiment, the bone image Gb is derived in the subtraction unit 63. Therefore, for the soft tissue regions in the first and second radiographic images G1 and G2, the weighting coefficient derivation unit 66 derives the ratio Gs1(x,y) / Gs2(x,y) of the pixel value Gs1(x,y) of the first radiographic image G1, which is a low-energy image, to the pixel value Gs2(x,y) of the second radiographic image G2, which is a high-energy image, as an index value representing attenuation, i.e., the weighting coefficient α in the above equation (1). Note that the ratio Gs1(x,y) / Gs2(x,y) represents the ratio μls / μhs of the attenuation coefficient μls for low-energy radiation to the attenuation coefficient μhs for high-energy radiation in soft tissue.

[0083] In the second embodiment, the subtraction unit 63 derives the bone image Gb by performing energy subtraction processing according to the above formula (1) using the weighting coefficient α derived by the weighting coefficient derivation unit 66. The weighting coefficient α in formula (1) is derived from the attenuation coefficient of the bones and the attenuation coefficient of the soft tissue derived by the weighting coefficient derivation unit 66.

[0084] In the second embodiment, the bone density deriving unit 64 uses the bone image Gb derived by the subtraction unit 63 to derive the bone density B and a representative value of the bone density B in the target bone.

[0085] Next, a third embodiment of the present disclosure will be described. Fig. 19 is a diagram showing the functional configuration of an information derivation device according to the third embodiment. In Fig. 19, the same components as those in Fig. 7 are assigned the same reference numerals, and detailed description thereof will be omitted. In the third embodiment, when deriving bone density as the ground truth data 42, new weighting coefficients to be used in weighted subtraction are derived based on pixel values ​​of bones contained in the bone image Gb, and a new bone image is derived by performing weighted subtraction on the first and second radiographic images G1 and G2 using the new weighting coefficients. Further, a new weighting coefficient is derived based on the new bone image, and a new bone image is derived based on the new weighting coefficient, and this process is repeated to derive the bone image Gb.

[0086] For this reason, as shown in FIG. 19, the information derivation device 50B according to the third embodiment further includes an initial weighting coefficient setting unit 67 and a weighting coefficient derivation unit 68 in addition to the components of the information derivation device 50 according to the first embodiment.

[0087] The initial weighting coefficient setting unit 67 sets initial weighting coefficients, which are initial values ​​of weighting coefficients when the subtraction unit 63 performs subtraction processing, based on the body thickness distribution when the scattered radiation removal unit 62 satisfies the termination condition. Here, in the third embodiment, the subtraction unit 63 derives a bone image Gb according to the above formula (1) using the initial weighting coefficients set by the initial weighting coefficient setting unit 67 and the weighting coefficient α derived by the weighting coefficient derivation unit 68.

[0088] The initial weighting coefficient setting unit 67 sets an initial weighting coefficient α0, which is an initial value of the weighting coefficient, based on the body thickness distribution when the scattered radiation removal unit 62 satisfies the termination condition. In the third embodiment, as shown in Fig. 20, a table LUT2 that defines the relationship between the body thickness distribution and the initial weighting coefficient α0 is stored in the storage 53. The initial weighting coefficient setting unit 67 sets the initial weighting coefficient α0 based on the body thickness distribution by referring to the table LUT2.

[0089] Here, since the degree of the beam hardening described above depends on the thickness ts of the soft tissue and the thickness tb of the bone tissue within the subject H, the attenuation coefficient μs of the soft tissue and the attenuation coefficient μb of the bone tissue can be defined as μs(ts,tb) and μb(ts,tb) as functions of ts and tb.

[0090] In energy subtraction processing, since there are images with two different energy distributions, the attenuation coefficient of the soft tissue of the low-energy image (first radiographic image G1 in this embodiment) can be expressed as μls(ts,tb), and the attenuation coefficient of the bone part can be expressed as μlb(ts,tb).Furthermore, the attenuation coefficient of the soft tissue of the high-energy image (second radiographic image G2 in this embodiment) can be expressed as μhs(ts,tb), and the attenuation coefficient of the bone part can be expressed as μhb(ts,tb).

[0091] To derive the bone image Gb, it is necessary to eliminate the contrast of soft tissue contained in the radiographic image. Therefore, the weighting coefficient α can be calculated using the ratio of the attenuation coefficients of soft tissue, α = μls(ts,tb) / μhs(ts,tb). In other words, the weighting coefficient α can be expressed as a function of the thickness of the soft tissue ts and the thickness of the bone tb.

[0092] In the third embodiment, the subtraction unit 63 first performs subtraction processing to perform weighted subtraction between corresponding pixels of the first and second radiographic images G1 and G2 using the initial weighting coefficient α0 set by the initial weighting coefficient setting unit 67. Thereafter, as will be described later, the subtraction processing is performed using the weighting coefficient αnew derived by the weighting coefficient derivation unit 68.

[0093] The weighting coefficient derivation unit 68 derives a new weighting coefficient αnew based on the pixel values ​​Gb(x,y) of the bones contained in the bone image Gb. Here, the pixel values ​​Gb(x,y) of the bones correspond to the thickness of the bones of the subject H. For this reason, in the third embodiment, a reference object simulating bones of various thicknesses is captured in advance, and a radiographic image of the reference object is obtained as a reference radiographic image. Then, using the relationship between the pixel values ​​of the region of the reference object in the reference radiographic image and the thickness of the reference object, a table defining the relationship between the pixel values ​​and thickness of the bones is derived in advance and stored in the storage 53. FIG. 21 is a diagram showing the table defining the relationship between the pixel values ​​and thickness of the bones. Table LUT3 shown in FIG. 21 indicates that the lower the pixel values ​​Gb(x,y) of the bones (i.e., the higher the brightness), the thicker the bones.

[0094] The weighting coefficient derivation unit 68 derives the bone thickness tb for each pixel of the bone image Gb from each pixel value Gb(x,y) of the bone image Gb by referring to the table LUT3. Note that areas in the bone image Gb where no bone exists consist only of soft tissue, and therefore the bone thickness tb is 0. On the other hand, for pixels in the bone image Gb where the bone thickness tb is not 0, the weighting coefficient derivation unit 68 derives the soft tissue thickness ts by subtracting the bone thickness tb from the body thickness distribution when the scattered radiation removal unit 62 satisfied the termination condition.

[0095] As described above, the weighting coefficient α can be expressed as a function of the soft tissue thickness ts and the bone tissue thickness tb. In the third embodiment, a table defining the relationship between the soft tissue thickness ts, the bone tissue thickness tb, and the weighting coefficient α is stored in the storage 53. FIG. 22 is a diagram showing a table defining the relationship between the soft tissue thickness ts, the bone tissue thickness tb, and the weighting coefficient α. As shown in FIG. 22, the table LUT4 three-dimensionally represents the relationship between the soft tissue thickness ts, the bone tissue thickness tb, and the weighting coefficient α. Here, in the table LUT4, the weighting coefficient α decreases as the soft tissue thickness ts and the bone tissue thickness tb increase.

[0096] In the third embodiment, multiple tables LUT4 are prepared according to the energy distribution of the radiation used during imaging and stored in the storage of the information deriving device 50B. The weighting coefficient derivation unit 68 acquires information on the energy distribution of the radiation used during imaging based on the imaging conditions, reads out the table LUT4 corresponding to the acquired energy distribution information from the storage, and uses it to derive the weighting coefficient. The weighting coefficient derivation unit 68 then derives a new weighting coefficient αnew by referring to the table LUT4 based on the derived bone thickness tb and soft tissue thickness ts.

[0097] The subtraction unit 63 uses the new weighting coefficient αnew derived by the weighting coefficient derivation unit 68 to derive a new bone image Gbnew according to the above equation (1).

[0098] Although the new bone image Gbnew may be used as the final bone image Gb, in the third embodiment, the derivation of the weighting coefficient α and the subtraction process are repeated.

[0099] That is, the weighting coefficient derivation unit 68 derives a new bone thickness tbnew by referring to table LUT3 based on the pixel values ​​of the bone in the new bone image Gbnew. Then, the weighting coefficient derivation unit 68 derives a difference Δtb between the new bone thickness tbnew and the bone thickness tb calculated in the previous process, and determines whether the difference Δtb is less than a predetermined threshold. If the difference Δtb is equal to or greater than the threshold, the weighting coefficient derivation unit 68 derives a new soft tissue thickness tsnew from the new bone thickness tbnew, and further derives a new weighting coefficient αnew based on the new bone thickness tbnew and the new soft tissue thickness tsnew by referring to table LUT4.

[0100] The subtraction unit 63 then performs subtraction processing using the new weighting coefficient αnew, and derives a new bone image Gbnew.

[0101] Then, the weighting coefficient derivation unit 68 derives a new bone thickness tbnew based on the new bone image Gbnew, and derives the difference Δtb between the new bone thickness tbnew and the bone thickness tb obtained in the previous processing.

[0102] In the third embodiment, the subtraction unit 63 and the weighting factor derivation unit 68 repeat the subtraction process and the derivation of the weighting factor αnew until the difference Δtb derived by the weighting factor derivation unit 68 becomes less than a predetermined threshold value.

[0103] In the third embodiment, the bone density deriving unit 64 derives the bone density B and a representative value of the bone density B of the target bone using the bone image Gb when the difference Δtb is less than the threshold value.

[0104] Next, a fourth embodiment of the present disclosure will be described. FIG. 23 is a diagram showing the functional configuration of an information derivation device according to the fourth embodiment. In FIG. 23, the same components as those in FIG. 7 are assigned the same reference numerals, and detailed description thereof will be omitted. In the fourth embodiment of the present disclosure, when deriving bone density as the correct answer data 42, the attenuation coefficient for each different energy distribution of soft tissue, the soft tissue thickness, the attenuation coefficient for each different energy distribution of bone tissue, and the bone thickness are changed from their initial values, and the difference between the value of (soft tissue attenuation coefficient × soft tissue thickness + bone tissue attenuation coefficient × bone tissue thickness) and each pixel value of the radiographic image is derived for each different energy distribution. The soft tissue attenuation coefficient and bone attenuation coefficient for each different energy distribution that minimizes the difference or is less than a predetermined threshold value are derived, and an energy subtraction process is performed using weighting coefficients derived based on the soft tissue attenuation coefficient and bone attenuation coefficient, thereby deriving a bone image Gb.

[0105] For this reason, as shown in FIG. 23, an information derivation device 50C according to the fourth embodiment further includes an initial value derivation unit 81, an attenuation coefficient derivation unit 82, and a weighting coefficient derivation unit 83 in addition to the components of the information derivation device 50 according to the first embodiment.

[0106] The initial value derivation unit 81 derives initial values ​​of the attenuation coefficient for each different energy distribution for soft tissue, the soft-tissue thickness, the attenuation coefficient for each different energy distribution for bone tissue, and the bone thickness, in order to derive weighting coefficients when performing energy subtraction processing. Specifically, the initial values ​​μls0, μhs0, ts0, μlb0, μhb0, tb0 of the soft-tissue attenuation coefficient μls for low-energy radiation, the soft-tissue attenuation coefficient μhs for high-energy radiation, the soft-tissue thickness ts, the bone attenuation coefficient μlb for low-energy radiation, the bone attenuation coefficient μhb for high-energy radiation, and the bone thickness tb are derived.

[0107] In the fourth embodiment, the subtraction unit 63 performs subtraction processing using weighting coefficients derived by the weighting coefficient derivation unit 83, as will be described later, to perform weighted subtraction between corresponding pixels of the first and second radiographic images G1, G2, as shown in the above equation (1), thereby deriving a bone image Gb in which bones in the subject H are extracted.

[0108] As described above, the soft tissue attenuation coefficient μs and the bone tissue attenuation coefficient μb can be defined as μs(ts,tb) and μb(ts,tb) as functions of ts and tb. Therefore, in the fourth embodiment, as in the third embodiment, the soft tissue attenuation coefficient of the low-energy image (the first radiographic image G1 in this embodiment) can be expressed as μls(ts,tb), and the bone tissue attenuation coefficient can be expressed as μlb(ts,tb). Furthermore, the soft tissue attenuation coefficient of the high-energy image (the second radiographic image G2 in this embodiment) can be expressed as μhs(ts,tb), and the bone tissue attenuation coefficient can be expressed as μhb(ts,tb).

[0109] In order to derive the bone image Gb, it is necessary to eliminate the contrast of soft tissue contained in the radiographic image. Therefore, the weighting coefficient α can be calculated using the ratio of the attenuation coefficients of soft tissue, α = μls(ts,tb) / μhs(ts,tb). In the following explanation, the attenuation coefficients μls(ts,tb), μhs(ts,tb), μlb(ts,tb), and μhb(ts,tb) will be simply referred to as the attenuation coefficients μls, μhs, μlb, and μhb, with (ts,tb) omitted.

[0110] The initial value derivation unit 81 uses the body thickness distribution when the scattered radiation removal unit 62 satisfies the termination condition as the initial value ts0 of the soft tissue thickness ts. In the fourth embodiment, the body thickness distribution used when performing scattered radiation removal processing is a body thickness distribution assuming that the subject H is composed only of soft tissue. Therefore, the initial value tb0 of the bone thickness tb is 0. Furthermore, the initial values ​​μls0, μhs0, μlb0, and μhb0 of the attenuation coefficients are derived based on the initial values ​​ts0 and tb0 of the soft and bone thicknesses ts and tb. In the fourth embodiment, since the initial value tb0 of the bone thickness tb is 0, the bone attenuation coefficients μlb0 and μhb0 are also 0. The soft tissue attenuation coefficients μls0 and μhs0 are derived based on the initial value ts0 of the soft tissue thickness ts. For this reason, in the fourth embodiment, a table that defines the relationship between the initial value ts0 of the soft-part thickness ts and the initial values ​​μls0 and μhs0 of the soft-part attenuation coefficients is stored in the storage 53.

[0111] 24 is a diagram showing a table that defines the relationship between the initial value ts0 of the soft-part thickness ts and the initial values ​​μls0 and μhs0 of the soft-part attenuation coefficients. The initial value derivation unit 81 derives the initial values ​​μls0 and μhs0 of the soft-part attenuation coefficients corresponding to the initial value ts0 of the soft-part thickness ts, with reference to the table LUT5 stored in the storage 53.

[0112] The attenuation coefficient deriving unit 82 derives the attenuation coefficients μ of soft tissue and μ of bone tissue for each different energy distribution. For energy subtraction processing, a low-energy image and a high-energy image are acquired by capturing an image of the subject H using radiation with different energy distributions. In this embodiment, the first radiographic image G1 is the low-energy image, and the second radiographic image G2 is the high-energy image. The pixel values ​​G1(x,y) of each pixel in the first radiographic image G1, which is the low-energy image, and the pixel values ​​G2(x,y) of each pixel in the second radiographic image G2, which is the high-energy image, are expressed by the following equations (3) and (4) using the soft tissue thickness ts(x,y), bone thickness tb(x,y), and attenuation coefficients μ of soft tissue at the corresponding pixel positions, μ of bone ... In addition, (x, y) is omitted in equations (3) and (4).

[0113] G1 = μls × ts + μlb × tb (3) G2=μhs×ts+μhb×tb (4)

[0114] In order to derive the weighting coefficient α for energy subtraction processing, it is necessary to derive the attenuation coefficients μls(x,y), μhs(x,y), μlb(x,y), and μhb(x,y). As described above, the attenuation coefficients μls(x,y), μhs(x,y), μlb(x,y), and μhb(x,y) are expressed as functions of the soft tissue thickness ts and the bone thickness tb. Therefore, in order to derive the attenuation coefficients μls(x,y), μhs(x,y), μlb(x,y), and μhb(x,y), it is necessary to derive the soft tissue thickness ts and the bone thickness tb. Solving equations (3) and (4) for ts and tb results in the following equations (5) and (6).

[0115] ts={μhb×G1-μlb×G2} / {μls×μhb-μlb×μhs}(5) tb={μls×G2-μhs×G1} / {μls×μhb-μlb×μhs}(6)

[0116] Here, the attenuation coefficients μls(x,y), μhs(x,y), μlb(x,y), and μhb(x,y) on the right-hand sides of equations (5) and (6) are expressed as functions of the soft tissue thickness ts and the bone thickness tb, so equations (5) and (6) cannot be solved algebraically.

[0117] For this reason, in the fourth embodiment, error functions EL and EH shown in the following equations (7) and (8) are set. The error functions EL and EH correspond to the difference between the value of (soft tissue attenuation coefficient)×(soft tissue thickness)+(bone attenuation coefficient)×(bone thickness) for each different energy distribution and each pixel value of the radiographic image. To simultaneously minimize the error functions EL and EH, the fourth embodiment sets an error function E0 shown in equation (9). Then, while changing the soft tissue thickness ts, bone thickness tb, and attenuation coefficients μls, μhs, μlb, and μhb from their initial values, a combination of soft tissue thickness ts and bone thickness tb that minimizes the error function E0 or makes the error function E0 less than a predetermined threshold is derived. In this case, it is preferable to derive the soft tissue thickness ts and bone thickness tb using an optimization algorithm such as the steepest descent method or the conjugate gradient method. The initial values ​​of the soft tissue thickness ts, bone thickness tb and attenuation coefficients μls, μhs, μlb, μhb used in this case are ts0, tb0, μls0, μhs0, μlb0, μhb0 derived by the initial value derivation unit 81.

[0118] EL=G1-{μls×ts+μlb×tb} (7) EH=G2-{μhs×ts+μhb×tb} (8) E0=EL 2 +EH 2 (9)

[0119] The attenuation coefficients used in the process of deriving the soft tissue thickness ts and the bone thickness tb are derived by referring to a table that defines the relationship between the predetermined soft tissue thickness ts and the bone thickness tb and the attenuation coefficients. Such a table is stored in the storage 53 of the information derivation device.

[0120] FIG. 25 is a diagram showing a table that defines the relationship between the soft tissue thickness ts and bone thickness tb and the attenuation coefficient. As shown in FIG. 25, table LUT6 three-dimensionally represents the relationship between the soft tissue thickness ts and bone thickness tb and the attenuation coefficient μ. Note that while FIG. 25 shows only one LUT6, a table is prepared for each of the attenuation coefficients μls, μhs, μlb, and μhb and is stored in storage. Here, table LUT6 indicates that the attenuation coefficient μ decreases as the soft tissue thickness ts and bone thickness tb increase.

[0121] The attenuation coefficient derivation unit 82 derives the soft tissue thickness ts and the bone thickness tb when the error function E0 is minimized or when the error function E0 is less than a predetermined threshold, and then derives the attenuation coefficients μls, μhs, μlb, and μhb by referring to table LUT6.

[0122] The weighting coefficient derivation unit 83 derives the weighting coefficient α used when the subtraction unit 63 performs subtraction processing. That is, the weighting coefficient derivation unit 83 derives the weighting coefficient α by performing the calculation α=μ / μ using the attenuation coefficients μ, μ, μ, and μ derived by the attenuation coefficient derivation unit 82.

[0123] In the fourth embodiment, the subtraction unit 63 derives the bone image Gb according to the above formula (1) using the weighting coefficient α derived by the weighting coefficient derivation unit 83. Then, the bone density derivation unit 64 derives the bone density B and a representative value of the bone density B in the target bone.

[0124] Next, a fifth embodiment of the present disclosure will be described. Fig. 26 is a diagram showing the functional configuration of an information derivation device according to the fifth embodiment. In Fig. 26, the same components as those in Fig. 7 are assigned the same reference numerals, and detailed description thereof will be omitted. In the fifth embodiment of the present disclosure, when deriving bone density as the ground truth data 42, the composition ratios of multiple components contained in the soft tissue of the subject H are derived, and attenuation coefficients for different energy distributions in the soft tissue are derived for each pixel of the first and second radiographic images G1 and G2 according to the composition ratios, and a subtraction process is performed using weighting coefficients derived based on the derived soft tissue attenuation coefficients and predetermined bone attenuation coefficients, thereby deriving a bone image Gb.

[0125] For this purpose, as shown in FIG. 26, an information derivation device 50D according to the fifth embodiment further includes a composition ratio derivation unit 84 and an attenuation coefficient setting unit 85 in addition to the components of the information derivation device 50 according to the first embodiment.

[0126] The composition ratio deriving unit 84 acquires the composition ratio of the subject H. In the fifth embodiment, the composition ratio deriving unit 84 acquires the composition ratio by deriving the composition ratio of the subject H based on the first and second radiographic images G1, G2. In the fifth embodiment, the composition ratio of fat is derived as the composition ratio. Therefore, although the subject H includes bones, for the sake of explanation, the first and second radiographic images G1, G2 will be described as including only soft tissue and not bones.

[0127] To derive the composition ratios, the composition ratio deriving unit 84 first derives the body thickness of the subject H as a first body thickness and a second body thickness for each pixel in each of the first and second radiographic images G1 and G2, respectively. Specifically, the composition ratio deriving unit 84 assumes that the luminance distribution of the first radiographic image G1 matches the body thickness distribution of the subject H, and converts the pixel values ​​of the first radiographic image G1 into thicknesses using the attenuation coefficient of radiation in the muscles of the subject H, thereby deriving the first body thickness t1 of the subject H. Furthermore, the composition ratio deriving unit 84 assumes that the luminance distribution of the second radiographic image G2 matches the body thickness distribution of the subject H, and converts the pixel values ​​of the second radiographic image G2 into thicknesses using the attenuation coefficient of the muscles of the subject H, thereby deriving the second body thickness t2 of the subject H.

[0128] Here, since the degree of the beam hardening described above depends on the fat thickness tf and muscle thickness tm within the subject H, the fat attenuation coefficient μf and the muscle attenuation coefficient μm can be defined as μf(tf,tm) and μm(tf,tm) as nonlinear functions of the fat thickness tf and muscle thickness tm.

[0129] In the fifth embodiment, the attenuation coefficient of fat for the first radiographic image G1, which is a low-energy image, can be expressed as μlf(tf,tm), and the attenuation coefficient of muscle can be expressed as μlm(tf,tm). Also, the attenuation coefficient of fat for the second radiographic image G2, which is a high-energy image, can be expressed as μhf(tf,tm), and the attenuation coefficient of muscle can be expressed as μhm(tf,tm).

[0130] Furthermore, the pixel value G1(x,y) of each pixel in the soft tissue region of the first radiographic image G1, which is a low-energy image, and the pixel value G2(x,y) of each pixel in the soft tissue region of the second radiographic image G2, which is a high-energy image, are expressed by the following equations (10) and (11), respectively, using the fat thickness tf(x,y), muscle thickness tm(x,y), and attenuation coefficients μlf(x,y), μhf(x,y), μlm(x,y), and μhm(x,y) at the corresponding pixel positions. Note that (x,y) is omitted in equations (10) and (11).

[0131] G1=μlf×tf+μlm×tm (10) G2=μhf×tf+μhm×tm (11)

[0132] As described above, in the fifth embodiment, when deriving the first body thickness t1 and the second body thickness t2, the pixel values ​​of the first radiographic image G1 and the second radiographic image G2 are converted into thicknesses using the attenuation coefficients of the muscles of the subject H. Therefore, in the fifth embodiment, the composition ratio deriving unit 84 derives the first body thickness t1 and the second body thickness t2 using the following equations (12) and (13). Note that (x, y) are omitted in equations (12) and (13).

[0133] t1=G1 / μlm (12) t2=G2 / μhm (13)

[0134] If the subject H contains only muscle at the pixel positions where the first and second body thicknesses t1 and t2 are derived, the first body thickness t1 and the second body thickness t2 will be the same. However, in the actual subject H, both muscle and fat are contained at the same pixel positions in the first and second radiographic images G1 and G2. Therefore, the first and second body thicknesses t1 and t2 derived using equations (12) and (13) will not match the actual body thickness of the subject H. Furthermore, when comparing the first body thickness t1 derived from the first radiographic image G1, which is a low-energy image, and the second body thickness t2 derived from the second radiographic image G2, which is a high-energy image, the first body thickness t1 will be greater than the second body thickness t2.

[0135] For example, as shown in Fig. 27, assume that the actual body thickness is 100 mm, and the thicknesses of fat and muscle are 30 mm and 70 mm, respectively. In this case, the first body thickness t1 derived from the first radiographic image G1 acquired using low-energy radiation is, for example, 80 mm, and the second body thickness t2 derived from the second radiographic image G2 acquired using high-energy radiation is, for example, 70 mm. Furthermore, the difference between the first body thickness t1 and the second body thickness t2 increases as the fat composition ratio increases.

[0136] Here, the difference between the first body thickness t1 and the second body thickness t2 varies depending on the composition ratio of fat and muscle in the subject H. For this reason, in the fifth embodiment, subject models with variously changed fat composition ratios are imaged using radiation with different energy distributions, and the body thickness is derived from each of the two radiographic images thus obtained. A table correlating the difference in body thickness derived from the two radiographic images with the fat composition ratio is created in advance and stored in storage 53.

[0137] Fig. 28 is a diagram showing a table associating the difference in body thickness derived from two radiographic images with the fat composition percentage. As shown in Fig. 28, the horizontal axis of table LUT7 represents the difference in body thickness derived from each of the two radiographic images, and the vertical axis represents the fat composition percentage. As shown in Fig. 28, the greater the difference in body thickness derived from each of the two radiographic images, the greater the fat composition percentage. Note that a table associating the difference in body thickness derived from each of the two radiographic images with the fat composition percentage is prepared for each energy distribution of radiation used during imaging, and is stored in storage 53.

[0138] The composition ratio derivation unit 84 derives the difference between the derived first body thickness t1 and second body thickness t2, and derives the fat composition ratio R(x, y) by referring to the LUT7 stored in the storage of the information derivation device 50D. Note that the muscle composition ratio can be derived by subtracting the derived fat composition ratio R(x, y) from 100%.

[0139] The attenuation coefficient setting unit 85 sets the attenuation coefficient of radiation used when acquiring the first and second radiographic images G1, G2 for each pixel of the first and second radiographic images G1, G2 according to the fat composition ratio R(x, y). Specifically, the attenuation coefficient setting unit 85 sets the attenuation coefficient of the soft tissue of the subject H. In the fifth embodiment, the first radiographic image G1 corresponds to a low-energy image, and the second radiographic image G2 corresponds to a high-energy image. Therefore, the attenuation coefficient setting unit 85 derives the soft-tissue attenuation coefficient μls(x, y) for the low-energy image and the soft-tissue attenuation coefficient μhs(x, y) for the high-energy image using the following equations (14) and (15). Note that (x, y) are omitted in equations (14) and (15). Furthermore, μlm is the attenuation coefficient of muscle in low-energy images, μlf is the attenuation coefficient of fat in low-energy images, μhm is the attenuation coefficient of muscle in high-energy images, and μhf is the attenuation coefficient of fat in high-energy images.

[0140] μls = (1-R) ​​× μlm + R × μlf (14) μhs=(1-R)×μhm+R×μhf (15)

[0141] In the fifth embodiment, the subtraction unit 63 performs subtraction processing using the attenuation coefficients μls and μhs set by the attenuation coefficient setting unit 85. At this time, the subtraction unit 63 derives the weighting coefficient α in the above equation (1). The weighting coefficient α used in the fifth embodiment is derived from α=μls / μhs using the attenuation coefficient set by the attenuation coefficient setting unit 85. Then, the subtraction unit 63 derives a bone image Gb according to the above equation (1) using the derived weighting coefficient α. Then, the bone density derivation unit 64 derives the bone density B and a representative value of the bone density B of the target bone.

[0142] Next, an information derivation device according to a sixth embodiment of the present disclosure will be described. Note that the configuration of the information derivation device according to the sixth embodiment is the same as the configuration of the information derivation device 50 according to the first embodiment, and only the processing performed by the scattered radiation removal unit 62 is different, so detailed description will be omitted here. Fig. 29 is a diagram showing the functional configuration of the scattered radiation removal unit in the information derivation device according to the sixth embodiment. As shown in Fig. 29, the scattered radiation removal unit 62A in the information derivation device according to the sixth embodiment includes an imaging condition acquisition unit 91, a body thickness derivation unit 92, a characteristic acquisition unit 93, a ray distribution derivation unit 94, and a calculation unit 95.

[0143] In the sixth embodiment, an imaging device 1A shown in Fig. 30 is used to capture an image of a subject H lying supine on an imaging table 4, further using an anti-scatter grid 8, to obtain first and second radiographic images G1, G2, and the first and second radiographic images G1, G2 are used as training data 40. In Fig. 30, the imaging table 4 has a tabletop 4A, and below the tabletop 4A, an anti-scatter grid (hereinafter simply referred to as the grid) 8, a first radiation detector 5, a filter 7, and a second radiation detector 6 are arranged in this order from the radiation source 3 side, and these are attached below the tabletop 4A by attachment parts 4B.

[0144] When generating the training data 40, the imaging condition acquisition unit 91 acquires from the image storage system 9 the imaging conditions used during energy subtraction imaging of the subject H to acquire the first and second radiographic images G1 and G2 as the learning data 41. In the sixth embodiment, the imaging conditions also include the radiation quality. The radiation quality is defined using one or more of the tube voltage [kV] of the radiation generator in the radiation source 3, the total filtration amount [mmAl equivalent], and the half-value layer [mmAl]. The tube voltage refers to the maximum value of the generated radiation energy distribution. The total filtration amount is the filtration amount of each component of the imaging device 1, such as the radiation generator and collimator in the radiation source 3, converted into aluminum thickness. The larger the total filtration amount, the greater the effect of beam hardening in the imaging device 1, resulting in a greater concentration of high-energy components in the radiation wavelength distribution. The half-value layer is defined as the thickness of aluminum required to attenuate the radiation dose by half relative to the generated radiation energy distribution. The thicker the aluminum in the half-value layer, the greater the concentration of high-energy components in the radiation wavelength distribution.

[0145] The body thickness derivation unit 92 derives the body thickness distribution of the subject H based on at least one of the first and second radiographic images G1, G2 and the imaging conditions. Hereinafter, the body thickness distribution derived by the body thickness derivation unit 92 will be referred to as the initial body thickness distribution T0. The derivation of the initial body thickness distribution T0 will be described below. Note that although the following description will focus on the derivation of body thickness and the elimination of scattered rays using the first radiographic image G1, the derivation of body thickness and the elimination of scattered rays can also be performed using the second radiographic image G2 in a similar manner.

[0146] First, when the radiation source 3 is driven to irradiate the radiation detector 5 with radiation in the absence of the subject H, the dose I0(x, y) of the radiation emitted from the radiation source 3 that reaches the radiation detector 5 is expressed by the following equation (16). In equation (16), mAs, which is included in the imaging conditions, is the tube current-time product, and kV is the tube voltage. Taking the half-value layer into consideration, the dose I0(x, y) is expressed by the following equation (16-1). Here, F is a nonlinear function that represents the amount of radiation that reaches the radiation detector 5 when a reference dose (e.g., 1 mAs) is irradiated to the radiation detector 5 in the absence of the subject H at a reference SID (e.g., 100 cm). F varies depending on the tube voltage or the tube voltage and the half-value layer. Furthermore, since the dose I0 is derived for each pixel of the radiographic image acquired by the radiation detector 5, (x, y) represents the pixel position of each pixel. In the following explanation, in order to include both cases where the half-value layer is taken into account and cases where it is not, the formulas will be expressed by including mmAl in parentheses, as shown in the following formula (16-2).

[0147] I0(x,y)=mAs×F(kV) / SID 2 (16) I0(x,y)=mAs×F(kV,mmAl) / SID 2 (16-1) I0(x,y)=mAs×F(kV(,mmAl)) / SID 2 (16-2)

[0148] Furthermore, if the initial body thickness distribution is T0, the attenuation coefficient of the subject H when the initial body thickness distribution is T0 is μ(T0), and the scatter-to-primary ratio, which is the ratio of the scattered radiation dose to the primary dose contained in the radiation after passing through the subject H with the initial body thickness distribution T0 when the spread of scattered radiation is not taken into account, is STPR(T0), the dose I1 after passing through the subject H is expressed by the following equation (17). Note that in equation (17), the initial body thickness distribution T0, the arrived dose I0, and the dose I1 are derived for each pixel of the plain radiographic image G0, but (x, y) are omitted. Furthermore, STPR is a nonlinear function that depends not only on the body thickness but also on the tube voltage [kV] and half-value layer [mmAl], but in equation (17), the notations of kV and mmAl are omitted. I1=I0×exp{-μ(T0)×T0}×{1+STPR(T0)} (17)

[0149] In equation (17), dose I1 is the pixel value for each pixel in plain radiographic image G0, and the arrival dose I0 is derived using equations (16) and (16-1) above. However, because F and STPR are nonlinear functions, equation (17) cannot be algebraically solved for T0. For this reason, the body thickness deriving unit 92 defines an error function E1 as shown in equation (18) or equation (18-1) below. Then, T0 that minimizes error function E1 or is less than a predetermined threshold value is derived as the initial body thickness distribution. In this case, the body thickness deriving unit 92 derives the initial body thickness distribution T0 using an optimization algorithm such as the steepest descent method or the conjugate gradient method.

[0150] E1=[I1-I0×exp{-μ(T0)×T0}×{1+STPR(T0)}] 2 (18) E1=|I1-I0×exp{-μ(T0)×T0}×{1+STPR(T0)}| (18-1)

[0151] The characteristic acquisition unit 93 acquires radiation characteristics of an object located between the subject H and the first and second radiation detectors 5, 6 during imaging. Here, when radiation that has passed through the subject H passes through an object located between the subject H and the radiation detector 5, the transmittance of the radiation changes depending on the radiation quality of the radiation that has passed through the subject H. Furthermore, the primary rays and scattered rays contained in the radiation that has passed through the subject H have different transmittances due to differences in the traveling direction and radiation quality of the radiation. For this reason, in the sixth embodiment, the primary ray transmittance and scattered ray transmittance of the object are used as the radiation characteristics of the object.

[0152] As described above, when the radiation after passing through the subject H passes through an object interposed between the subject H and the radiation detector 5, the transmittance of the radiation changes depending on the radiation quality after passing through the subject H. Furthermore, the radiation quality after passing through the subject H depends on the body thickness distribution T of the subject H. For this reason, the primary ray transmittance and scattered ray transmittance can be expressed as functions of the body thickness distribution T of the subject H, as Tp(T) and Ts(T), respectively.

[0153] Furthermore, the radiation quality of the radiation after passing through the subject H also depends on the radiation quality of the radiation source 3, which is included in the imaging conditions. The radiation quality depends on the tube voltage and half-value layer. Therefore, strictly speaking, the primary ray transmittance and the scattered ray transmittance are expressed as Tp(kV(,mmAl),T) and Ts(kV(,mmAl),T), respectively. In the following explanation, the primary ray transmittance and the scattered ray transmittance may be simply expressed as Tp and Ts.

[0154] Here, the primary ray transmittance Tp and scattered ray transmittance Ts of an object interposed between the subject H and the radiation detector 5 depend on the body thickness distribution T of the subject H, as described above. For this reason, in the sixth embodiment, phantoms having various thicknesses that mimic the body thickness distribution T of the subject are used to measure the primary ray transmittance Tp and scattered ray transmittance Ts of the object according to the body thickness distribution T of the subject H, and a table that defines the relationship between the body thickness distribution T of the subject H and the primary ray transmittance Tp and scattered ray transmittance Ts of the object is generated based on the measurement results, and stored in the storage of the information derivation device according to the sixth embodiment. Measurement of the primary ray transmittance Tp and scattered ray transmittance Ts of the object according to the body thickness distribution T of the subject H will now be described.

[0155] First, the calculation of scattered ray transmittance Ts will be described. FIGS. 31 and 32 are diagrams for explaining the measurement of scattered ray transmittance Ts according to the body thickness of the subject H. First, as shown in FIG. 31 , a phantom 101 simulating a human body is placed on the surface of the radiation detector 5, and a lead plate 102 is placed on the phantom 101. The phantom 101 has various thicknesses, such as 5 cm, 10 cm, and 20 cm, and is made of a material such as acrylic that has a radiation transmittance similar to that of water. In this state, the radiation source 3 is driven to irradiate the radiation detector 5 with radiation, and the characteristic acquisition unit 93 acquires a radiation image K0 for measurement. The signal value of the radiation image K0 is large in the region of the radiation detector 5 that is directly irradiated with radiation, and decreases in the region of the phantom 101 and the region of the lead plate 102, in that order.

[0156] Since the lead plate 102 does not transmit radiation, the signal value in the area of ​​the lead plate 102 in the radiographic image K0 should be 0. However, radiation scattered by the phantom 101 reaches the area of ​​the radiation detector 5 corresponding to the lead plate 102. Therefore, the area of ​​the lead plate 102 in the radiographic image K0 has a signal value S0 corresponding to the scattered radiation component caused by the phantom 101.

[0157] Next, as shown in FIG. 32 , a phantom 101 is placed on the tabletop 4A of the radiography device 1, and a lead plate 102 is further placed on the phantom 101. Then, in the same manner as when radiographing the subject H, a radiation detector 5 and a grid 8 are disposed below the tabletop 4A. The radiation source 3 is driven to irradiate the radiation detector 5 with radiation, and the characteristic acquisition unit 93 acquires a radiographic image K1 for measurement. As with the radiographic image K0, the signal value of the radiographic image K1 is large in the area of ​​the radiation detector 5 that is directly irradiated with radiation, and decreases in the order of the area of ​​the phantom 101 and the area of ​​the lead plate 102. Here, as shown in FIG. 32 , when radiography is performed with the tabletop 4A and the grid 8 interposed between the phantom 101 and the radiation detector 5, not only the radiation scattered by the phantom 101 but also the radiation scattered by the tabletop 4A and the grid 8 reaches the area of ​​the radiation detector 5 corresponding to the lead plate 102. Therefore, the region of the lead plate 102 in the radiation image K1 has a signal value S1 corresponding to the scattered radiation components caused by the phantom 101, the table top 4A, and the grid 8.

[0158] Note that signal value S1 includes scattered ray components caused by the tabletop 4A and grid 8, and is therefore greater than signal value S0 shown in Fig. 31. Therefore, when imaging a phantom 101 having a thickness of t, the scattered ray transmittance Ts of the objects interposed between the subject H and the radiation detector 5, i.e., the tabletop 4A and grid 8, can be calculated by S1 / S0.

[0159] In the sixth embodiment, the characteristic acquisition unit 93 uses at least two types of phantoms with different thicknesses to calculate the scattered ray transmittance Ts corresponding to each thickness as shown in Figures 31 and 32. Furthermore, the characteristic acquisition unit 93 derives the scattered ray transmittance Ts for thicknesses not present in the phantom 101 by interpolating the scattered ray transmittances Ts for the multiple measured thicknesses. In this way, the characteristic acquisition unit 93 interpolates the scattered ray transmittances for thicknesses between the respective thicknesses to generate a table LUT8 that indicates the relationship between the body thickness of the subject H and the scattered ray transmittance Ts of objects interposed between the subject H and the radiation detector 5, as shown in Figure 33.

[0160] Next, calculation of primary ray transmittance will be described. FIGS. 34 and 35 are diagrams for explaining measurement of primary ray transmittance Tp according to the body thickness of the subject H. First, as shown in FIG. 34, a phantom 101 simulating a human body is placed on the surface of the radiation detector 5. Here, the phantom 101 is the same as that used when deriving the scattered ray transmittance Ts. In this state, the radiation source 3 is driven to irradiate the radiation detector 5 with radiation, and the characteristic acquisition unit 93 acquires a radiation image K2 for measurement. A signal value S2 of a region in the radiation image K2 corresponding to the phantom 101 includes both the primary ray component and the scattered ray component of the radiation that has passed through the phantom 101. Here, the scattered ray component of the radiation that has passed through the phantom 101 is the signal value S0 in the radiation image K0 calculated using the method shown in FIG. 31 above. Therefore, the primary ray component of the radiation that has passed through the phantom 101 is calculated by S2 - S0.

[0161] 35, a phantom 101 is placed on the tabletop 4A of the radiography device 1, and a radiation detector 5 and a grid 8 are arranged below the tabletop 4A in the same manner as when radiographing a subject H. The radiation source 3 is then driven to irradiate the radiation detector 5 with radiation, and the characteristic acquisition unit 93 acquires a radiographic image K3 for measurement. A signal value S3 of the region corresponding to the phantom 101 in the radiographic image K3 includes both the primary ray component and the scattered ray component of the radiation that has passed through the phantom 101, the tabletop 4A, and the grid 8. The scattered ray component of the radiation that has passed through the phantom 101, the tabletop 4A, and the grid 8 is the signal value S1 in the radiographic image K1 obtained by the method shown in FIG. 32 above. Therefore, the primary ray component of the radiation that has passed through the phantom 101, the tabletop 4A, and the grid 8 is derived by S3-S1.

[0162] Therefore, when the phantom 101 is imaged, the primary ray transmittance Tp of the tabletop 4A and grid 8 located between the subject H and the radiation detector 5 can be calculated by (S3-S1) / (S2-S0). In the sixth embodiment, the characteristic acquisition unit 93 uses at least two types of phantoms with different thicknesses to calculate the primary ray transmittance Tp corresponding to each thickness as shown in FIGS. 34 and 35. Furthermore, the characteristic acquisition unit 93 derives the primary ray transmittance Tp of a thickness not present in the phantom 101 by interpolating the primary ray transmittances Tp for the measured thicknesses. As a result, the characteristic acquisition unit 93 generates a table LUT9 that indicates the relationship between the body thickness of the subject H and the primary ray transmittance Tp of objects located between the subject H and the radiation detector 5, as shown in FIG.

[0163] The tables LUT8 and LUT9 generated as described above are stored in the storage 53 of the information deriving device according to the sixth embodiment. The tables are generated according to various imaging conditions (i.e., radiation quality, dose, and radiation source distance) and the type of grid 8 to be used, and are stored in the storage 13.

[0164] The characteristic acquisition unit 93 references the tables LUT8 and LUT9 stored in the storage 53 in accordance with the imaging conditions acquired by the imaging condition acquisition unit 91, and acquires the primary ray transmittance Tp(T0) and scattered ray transmittance Ts(T0) corresponding to the initial body thickness distribution T0 for an object interposed between the subject H and the radiation detector 5. Note that the primary ray transmittance Tp and scattered ray transmittance Ts also depend on the radiation quality, and therefore the primary ray transmittance Tp and scattered ray transmittance Ts can be expressed as Tp(kV(,mmAl),T0) and Ts(kV(,mmAl),T0), respectively.

[0165] The ray distribution derivation unit 94 derives the primary ray distribution and scattered ray distribution of the radiation detected by the radiation detector 5 using the imaging conditions, body thickness distribution, and radiation characteristics of objects interposed between the subject H and the radiation detector 5. Here, the primary ray distribution Ip0 and scattered ray distribution Is0 of the radiation after passing through the subject H are expressed by the following equations (19) and (20), where T is the body thickness distribution. The PSF in equation (20) is a point spread function that represents the distribution of scattered rays spreading from one pixel, and is defined according to the radiation quality and body thickness. In addition, * indicates a convolution operation. The primary ray distribution Ip0 and scattered ray distribution Is0 are derived for each pixel of the plain radiographic image G0, but (x, y) are omitted in equations (19) and (20). In addition, in the sixth embodiment, as will be described later, the body thickness distribution, primary ray distribution Ip0, and scattered ray distribution Is0 are repeatedly derived, but when deriving the primary ray distribution Ip0 and scattered ray distribution Is0 for the first time, the initial body thickness distribution T0 is used as the body thickness distribution T.

[0166] Ip0=I0×exp{-μ(T)×T} (19) Is0=Ip0×STPR(kV(,mmAl),T)*PSF(kV(,mmAl),T) (20)

[0167] Furthermore, the ray distribution derivation unit 94 derives the primary ray distribution Ip1 and scattered ray distribution Is1 that reach the radiation detector 5 using the primary ray transmittance Tp and scattered ray transmittance Ts of objects interposed between the subject H and the radiation detector 5, according to the following equations (21) and (22). Furthermore, the sum Iw1 of the primary ray distribution Ip1 and scattered ray distribution Is1 is derived according to the following equation (23). In equations (21) and (22), the initial body thickness distribution T0 is used as the body thickness distribution T when deriving the primary ray distribution Ip1 and scattered ray distribution Is1 the first time.

[0168] Ip1=Ip0×Tp(kV(,mmAl),T) (21) Is1 = Is0 × Ts(kV(,mmAl),T) (22) Iw1=Ip1+Is1 (23)

[0169] The calculation unit 95 derives the error E2 between the sum Iw1 of the primary ray distribution Ip1 and the scattered ray distribution Is1 and the dose at each pixel position of the first radiographic image G1, i.e., the pixel value I1. The error E2 is derived using the following equation (24) or equation (24-1). In equations (24) and (24-1), N represents the number of pixels in the first radiographic image G1, and Σ represents the sum over all pixels in the first radiographic image G1. Note that equation (24-1) calculates I1 / Iw1 within log, and therefore the error E2 can be derived independently of the dose irradiated to the subject H, i.e., the reached dose I0.

[0170] E2=(1 / N)×Σ{I1-Iw1} 2 (twenty four) E2=(1 / N)×Σ|log{I1 / Iw1}| (24-1)

[0171] The calculation unit 95 then updates the body thickness distribution T so that the error E2 is minimized or becomes less than a predetermined threshold value. The calculation unit 95 then repeatedly acquires the primary ray transmittance Tp and the scattered ray transmittance Ts and derives the primary ray distribution Ip1 and the scattered ray distribution Is1 based on the updated body thickness distribution. Here, the calculation performed by the calculation unit 95 is referred to as a repetitive calculation. In the sixth embodiment, the calculation unit 95 performs repetitive calculations so that the error E2 becomes less than a predetermined threshold value. The calculation unit 95 then outputs a processed first radiographic image Gc1 having pixel values ​​that are the primary ray distribution Ipc derived based on the body thickness distribution Tc of the subject H for which the error E2 is less than the predetermined threshold value.

[0172] The repeated acquisition of the primary ray transmittance Tp and scattered ray transmittance Ts and the repeated derivation of the primary ray distribution Ip1 and scattered ray distribution Is1 are performed by the characteristic acquisition unit 93 and the line distribution derivation unit 94, respectively.

[0173] Meanwhile, a primary ray distribution Ipc is derived for the second radiographic image G2 in the same manner as for the first radiographic image G1. The primary ray distribution for the first radiographic image G1 is designated Ipc-1, and the primary ray distribution for the second radiographic image G2 is designated Ipc-2. The calculation unit 95 then outputs a processed second radiographic image Gc2 with the primary ray distribution Ipc-2 as pixel values.

[0174] In the sixth embodiment, a subtraction unit 63 derives a bone image Gb using the processed first and second radiographic images Gc1 and Gc2. Then, a bone density derivation unit 64 derives a bone density B and a representative value of the bone density B of the target bone using the bone image Gb derived by the subtraction unit 63.

[0175] The trained neural network 23A constructed by performing training using the bone density B derived in the sixth embodiment as correct answer data outputs a bone density that takes into account an object intervening between the subject H and the radiation detector when a simple radiographic image G0 obtained by simply imaging the subject H using the imaging device 1A shown in FIG. 30 is input.

[0176] Furthermore, in the sixth embodiment, the top plate 4A and grid 8 of the imaging table 4 are used as objects interposed between the subject H and the radiation detector 5. However, as shown in FIG. 37, there are cases where an air layer 103 is interposed between the top plate 4A and the grid 8. In such cases, it is preferable that the ray distribution derivation unit 94 derives the primary ray distribution Ip1 and the scattered ray distribution Is1 by including the air layer 103 in the objects interposed between the subject H and the radiation detector 5. In this case, the primary ray distribution Ip1 and the scattered ray distribution Is1 may be derived by convolving the point spread function PSFair(kV(,mmAl),tair) corresponding to the thickness tair of the air layer 103 with the above equations (21) and (22), as shown in the following equations (21-1) and (22-1). The thickness tair of the air layer 103 is determined by the distance between the bottom surface of the top plate 4A and the grid 8. This is the distance to the surface on the subject H side.

[0177] Ip1=Ip0×Tp(kV(,mmAl),T)*PSF air (kV(,mmAl),t air ) (21-1) Is1=Is0×Ts(kV(,mmAl),T)*PSF air (kV(,mmAl),t air ) (22-1)

[0178] Next, an information derivation device according to a seventh embodiment of the present disclosure will be described. Note that the configuration of the information derivation device according to the seventh embodiment is the same as the configuration of the information derivation device according to the first embodiment, and only the processing performed by the scattered radiation removal unit 62 is different, so detailed description will be omitted here. FIG. 38 is a diagram showing the functional configuration of the scattered radiation removal unit in the information derivation device according to the seventh embodiment. As shown in FIG. 38, the scattered radiation removal unit 62B in the information derivation device according to the seventh embodiment includes a first derivation unit 97, a second derivation unit 98, and an image generation unit 99.

[0179] In the information derivation device according to the seventh embodiment, a first derivation unit 97 derives a first primary ray distribution and a scattered ray distribution of radiation that has passed through the subject H using the first and second radiographic images G1 and G2, a second derivation unit 98 derives a second primary ray distribution and a scattered ray distribution of radiation that has passed through the object using the first primary ray distribution and the scattered ray distribution and the radiation characteristics of an object interposed between the subject H and the radiation detector that detects the radiographic image, and an image generation unit 99 derives radiographic images of the radiation after passing through the subject and the object using the second primary ray distribution and the scattered ray distribution, thereby performing scattered ray removal processing. Note that the scattered ray removal processing performed by the information derivation device according to the seventh embodiment is described in International Publication No. 2020 / 241664. Below, the scattered ray removal processing from the first radiographic image G1 will be described, but the scattered ray removal processing can also be performed on the second radiographic image G2 in a similar manner.

[0180] The first derivation unit 97 uses the first radiographic image G1 to estimate the components (primary ray components and scattered ray components) of the radiation that has passed through the subject H. In the derivation process performed by the first derivation unit 97 (hereinafter referred to as the first derivation process), the "radiation that has passed through the subject H" refers to the radiation that has passed through the subject H but has not yet passed through objects such as the tabletop 4A and the grid 8.

[0181] Furthermore, the components of radiation that have passed through the subject H specifically refer to the components of radiation that have passed through the subject H and / or the components of radiation that have been scattered by the subject H. In other words, the components of radiation that have passed through the subject H are the primary ray components after passing through the subject H. The components of radiation that have been scattered by the subject H are the scattered ray components after passing through the subject H. Regarding radiation that is incident on the subject H toward an arbitrary position X, if the subject H is considered to be an operator g1 that generates primary rays and an operator h1 that generates scattered ray components, then as shown in FIG. 39, the primary ray component after passing through the subject H is g1(X), and the scattered ray component after passing through the subject H is h1(X).

[0182] The first derivation unit 97 uses the first radiographic image G1 to estimate the primary ray component g1(X) after passing through the subject H, the scattered ray component h1(X) after passing through the subject H, or both. In the seventh embodiment, the first derivation unit 97 uses the first radiographic image G1 to estimate the primary ray component g1(X) after passing through the subject H and the scattered ray component h1(X) after passing through the subject H.

[0183] When estimating the primary ray component g1(X) after passing through the subject H from the first radiographic image G1, the first derivation unit 97 subtracts the estimated primary ray component g1(X) from the first radiographic image G1 to estimate the scattered ray component h1(X) after passing through the subject H. When estimating the scattered ray component h1(X) after passing through the subject H from the first radiographic image G1, the first derivation unit 97 subtracts the estimated scattered ray component h1(X) from the first radiographic image G1 to estimate the primary ray component g1(X) after passing through the subject H.

[0184] The first derivation process performed by the first derivation unit 97 can be performed, for example, by estimating the body thickness of the subject H using the first radiographic image G1, and then estimating the components of the radiation that have passed through the subject H using the estimated body thickness of the subject H. In this case, the first derivation unit 97 estimates, based on the estimated body thickness of the subject H, for each pixel of the first radiographic image G1 (or for each predetermined section consisting of a plurality of pixels), a primary ray component g1(X) of the radiation that has passed through the subject H and a scattered ray component h1(X) of the radiation that has been scattered by the subject H.

[0185] For example, as shown in FIG. 40, the pixel value V2 when subject H is present (“subject present”) is smaller than the pixel value V1 when subject H is not present (“no subject”). This is due to absorption by subject H, etc. Therefore, the difference Δ (=V1-V2) between these values ​​is related to the body thickness of subject H. On the other hand, the pixel value V1 when subject H is not present can be determined from the pixel value of the region where radiation reaches the radiation detector 5 without passing through subject H (direct region), or from a prior experiment (imaging without subject H). Therefore, the first derivation unit 97 can estimate the body thickness of subject H from the pixel value V2 of the first radiographic image G1 captured with subject H present.

[0186] Furthermore, the primary ray component g1(X) and scattered ray component h1(X) after passing through the subject H are both related to the body thickness of the subject H. For example, the thicker the body of the subject H, the less the primary ray component g1(X) due to absorption by the subject H and the more the scattered ray component h1(X) relative to the incident radiation. These properties of the subject H, i.e., the amount of radiation transmitted and scattered by the subject H for radiation having a specific energy, can be determined in advance by experiments or the like prior to radiography.

[0187] For this reason, the first derivation unit 97 stores, for example, characteristics related to the amount of transmission and the amount of scattering (hereinafter referred to as subject scattering characteristics) in the form of a function, a table, or the like for each subject H or each imaging region of the subject H. Then, by using the energy of the radiation used for imaging and the estimated actual body thickness of the subject H to determine the amount of transmission and the amount of scattering of the radiation, the primary ray component g1(X) and the scattered ray component h1(X) after transmission through the subject H are estimated.

[0188] The derivation result output by the first derivation unit 97 (hereinafter referred to as the first derivation result) is the primary ray component g1(X) at position P1 after passing through the subject H, the scattered ray component h1(X) at position P1 after passing through the subject H, or the intensity distribution f1(X) of the radiation at position P1 after passing through the subject H. The intensity distribution f1(X) of the radiation at position P1 is, for example, the sum or weighted sum of the primary ray component g1(X) and the scattered ray component h1(X). In the seventh embodiment, the first derivation unit 97 outputs the intensity distribution f1(X) of the radiation at position P1 after passing through the subject H as the first derivation result, for example, in the form of an image or in the form of a collection of data from which an image can be constructed. Note that the first derivation unit 97 can also output either the primary ray component g1(X) or the scattered ray component h1(X) after passing through the subject H as the derivation result.

[0189] The second derivation unit 98 estimates the components of the radiation that have passed through an object, using the derivation results of the first derivation unit 97 and the scattering characteristics of objects such as the tabletop 4A and grid 8, through which the radiation further passes after passing through the subject H. In the derivation process of the second derivation unit 98 (hereinafter referred to as the second derivation process), "passed through an object" means that the subject H has passed through a certain position and then passed through the object. Therefore, this also includes cases where the radiation has passed directly through the object without passing through the subject H, depending on the specific shape of the subject H, etc.

[0190] Specifically, the second derivation unit 98 estimates the radiation components that have passed through the subject H and the object, or the radiation components that have been scattered by at least one of the subject H and the object. The radiation components that have passed through the subject H and the object are the primary ray components after passing through the object. The radiation components that have been scattered by at least one of the subject H and the object are the scattered ray components after passing through the object.

[0191] The scattering characteristics of an object determine the distribution of the amount of radiation transmitted through the object and / or the amount of radiation scattered by the object. In the seventh embodiment, the scattering characteristics f2(X) include a first characteristic g2(X) that determines the distribution of the amount of radiation transmitted through the object and a second characteristic h2(X) that determines the distribution of the amount of radiation scattered by the object. Specifically, the scattering characteristics f2(X) are the sum or weighted sum of the first characteristic g2(X) and the second characteristic h2(X), for example, f2(X) = g2(X) + h2(X).

[0192] The first characteristic g2(X) is a function, a table, or the like that determines the transmission dose of radiation that is incident on the object directly toward an arbitrary position X without passing through the subject H. The second characteristic h2(X) is a function, a table, or the like that determines the transmission dose of radiation that is incident on the object directly toward an arbitrary position X without passing through the subject H. For example, if the object consists only of the table 4A of the imaging table 4, the first characteristic g2(X) determines the distribution of the transmission dose of the table 4A, and the second characteristic h2(X) determines the distribution of the scattered dose of the table 4A. The specific configuration of the object (whether the imaging table 4, etc. is in use or not) is known before radiography. Therefore, the first characteristic g2(X) and the second characteristic h2(X) can be obtained in advance by experiment, for example, for each specific configuration of the object or for each combination of objects. Furthermore, if an object is considered to generate a primary ray component and a scattered ray component from incident radiation, the first characteristic g2(X) is an operator that generates a primary ray component according to the incident radiation, and the second characteristic h2(X) is an operator that generates a scattered ray component according to the incident radiation.

[0193] In the seventh embodiment, the second derivation unit 98 holds in advance the first characteristic g2(X) and the second characteristic h2(X), for example, for each specific configuration of the object. As a result, the second derivation unit 98 holds in advance the scattering characteristic f2(X) of the object. However, the second derivation unit 98 can acquire the first characteristic g2(X), the second characteristic h2(X), and / or the scattering characteristic f2(X) as necessary.

[0194] As shown in Fig. 41, the intensity distribution of radiation (X) incident toward an arbitrary point X0 after passing through an object can be approximated by a PSF (point spread function) 120. The PSF 120 is, for example, a Gaussian function. Of the radiation (X) incident on an object toward the arbitrary point X0, the component that reaches the arbitrary point X0 and its vicinity is a distribution 121 of primary ray components, and the portion of the PSF 120 excluding the distribution 121 of primary ray components is a distribution 122 of scattered ray components.

[0195] Furthermore, since the energy of the radiation used for imaging, and the material (density, etc.) and thickness (mass) of the object such as the tabletop 4A are known, the specific shape of the PSF 120, such as the peak height and half-width, is predetermined. Therefore, for example, the second characteristic h2(X) can be obtained in advance by performing a deconvolution operation of the above-mentioned scattered radiation component distribution 122 on a radiographic image obtained by imaging without the subject H in place. The first characteristic g2(X) can be obtained in advance by subtracting the second characteristic h2(X) from a radiographic image obtained by capturing the image without placing a radiographer or by performing a deconvolution operation on the distribution 121 of the primary ray components.

[0196] The second derivation unit 98 estimates the components of the radiation that have transmitted through the object by applying the scattering characteristics of the object to the first derivation result, which is the derivation result of the first derivation unit 97. Specifically, the object is exposed to radiation having a distribution represented by the first derivation result. Therefore, the second derivation unit 98 estimates the components of the radiation that have transmitted through the object by using the first derivation result (f1(X)) as the argument of the scattering characteristics f2(X) of the object. That is, the second derivation unit 98 estimates the components of the radiation that have transmitted through the object by calculation based on the following equation (25). In the seventh embodiment, the first derivation result is f1(X) = g1(X) + h1(X), and therefore the above equation (25) can be expressed as the following equation (26) and expanded as shown in equation (27).

[0197] f2(f1(X))=g2(f1(X))+h2(f1(X)) (25) f2(f1(X))=g2(g1(X)+h1(X))+h2(g1(X)+h1(X)) (26) f2(f1(X))=g2g1(X)+g2h1(X)+h2g1(X)+h2h1(X) (27)

[0198] As shown in FIG. 42, "g2g1(X)" in the first term on the right side of the above equation (27) represents ray Ra1, which is part of the radiation used for imaging, that passes through the subject H and the object (tabletop 4A is shown in FIG. 42) to reach pixel P(X0) at an arbitrary point X0. "g2h1(X)" in the second term on the right side of the above equation (27) represents ray Ra2, which is part of the radiation used for imaging, that is scattered by scatterer D1 contained in the subject H, then passes through the object, and reaches pixel P(X0) at an arbitrary point X0. "h2g1(X)" in the third term on the right side of the above equation (27) represents ray Ra3, which is part of the radiation used for imaging, that is scattered by scatterer D3 contained in the object, and then reaches pixel P(X0) at an arbitrary point X0. Furthermore, the fourth term on the right side of equation (27), “h2h1(X),” represents the ray Ra4 used for imaging, which is scattered by the scatterer D2 contained in the subject H, and then further scattered by the scatterer D4 contained in the object, and reaches the pixel P(X0) at an arbitrary point X0.

[0199] As described above, the second derivation unit 98 obtains the first term "g2g1(X)" and / or the sum of the second to fourth terms "g2h1(X)+h2g1(X)+h2h1(X)" of equation (27). This is because the first term "g2g1(X)" of equation (27) represents the distribution of primary ray components after passing through an object, and the sum of the second to fourth terms "g2h1(X)+h2g1(X)+h2h1(X)" represents the distribution of scattered ray components after passing through an object. In the seventh embodiment, the second derivation unit 98 obtains the distribution g2g1(X) of the primary ray components after passing through an object and outputs it as a derivation result.

[0200] The image generation unit 99 uses the derivation result of the second derivation unit 98 to generate a processed radiographic image that forms an image of the subject H using radiation that has passed through the subject H and the object. When the second derivation unit 98 estimates primary ray components of radiation that have passed through the subject H and the object, the image generation unit 99 generates a processed radiographic image by imaging the second derivation result that is the derivation result of the second derivation unit 98. When the second derivation unit 98 estimates scattered ray components of radiation that have been scattered by the subject H or the object, the image generation unit 99 generates a processed radiographic image by subtracting the second derivation result that is the derivation result of the second derivation unit 98 from the first radiographic image G1.

[0201] In the seventh embodiment, the second derivation unit 98 outputs the distribution of primary ray components after passing through an object, and the image generation unit 99 generates a processed radiographic image by imaging this. Therefore, the distribution g2g1(X) of primary ray components output by the second derivation unit 98 is a processed radiographic image from which scattered ray components have essentially been removed. Note that the image generation unit 99 can perform various image processing (for example, contrast adjustment processing or structure emphasis processing) on ​​the generated processed radiographic image as needed.

[0202] The scattered radiation removal processing according to the sixth and seventh embodiments may be performed in the first to fifth embodiments. In this case, the information derivation devices 50A to 50D have a scattered radiation removal unit 62A or a scattered radiation removal unit 62B instead of the scattered radiation removal unit 62.

[0203] Next, an eighth embodiment of the present disclosure will be described. FIG. 43 is a diagram showing the functional configuration of an information derivation device according to the eighth embodiment. In FIG. 43, the same components as those in FIG. 7 are assigned the same reference numerals, and detailed description thereof will be omitted. In the seventh embodiment of the present disclosure, graininess reduction processing is performed on the first and second radiographic images G1, G2, and energy subtraction processing is performed using the first and second radiographic images G1, G2 that have been subjected to the graininess reduction processing. For this reason, as shown in FIG. 43, an information derivation device 50E according to the eighth embodiment further includes a processing content derivation unit 86 and a graininess reduction processing unit 87 in addition to the information derivation device 50 according to the first embodiment.

[0204] The processing content derivation unit 86 derives the processing content of the first graininess suppression processing for the first radiographic image G1, and derives the processing content of the second graininess suppression processing for the second radiographic image G2 based on the processing content of the first graininess suppression processing.

[0205] In this embodiment, the subject H is imaged using the one-shot method to obtain first and second radiographic images G1 and G2. In the one-shot method, radiation that has passed through the subject H is irradiated onto two radiation detectors 5 and 6 that are stacked with a radiation energy converting filter 7 interposed therebetween. As a result, the second radiation detector 6, which is located farther from the radiation source 3, receives a smaller radiation dose than the first radiation detector 5, which is located closer to the radiation source 3. As a result, the second radiographic image G2 has more radiation quantum noise and a lower S / N ratio than the first radiographic image G1. For this reason, it is necessary to perform graininess reduction processing, particularly on the second radiographic image G2, to reduce graininess caused by quantum noise.

[0206] The processing content derivation unit 86 derives the processing content of the first graininess suppression processing for the first radiographic image G1, which has a higher S / N ratio, of the first radiographic image G1 and the second radiographic image G1. The processing content derivation unit 86 then derives the processing content of the second graininess suppression processing for the second radiographic image G2 based on the processing content of the first graininess suppression processing. The derivation of the processing content will be described below.

[0207] Examples of graininess reduction processing include filtering using a smoothing filter such as a Gaussian filter having a predetermined size, such as 3 × 3 or 5 × 5, centered on the pixel of interest. However, using a Gaussian filter may blur the edges of structures included in the first and second radiographic images G1 and G2. For this reason, in the eighth embodiment, graininess reduction processing is performed using an edge-preserving smoothing filter that suppresses graininess while preventing edge blurring. As the edge-preserving smoothing filter, a bilateral filter is used that weights pixels adjacent to the pixel of interest according to a normal distribution, such that the weight decreases the further away the pixel is from the pixel of interest and the greater the difference in pixel value between the pixel of interest and the pixel of interest.

[0208] Fig. 44 is a diagram showing an example of a bilateral filter for a first radiographic image G1. Fig. 44 shows two 5 × 5 pixel local regions A1 near an edge included in the first radiographic image G1, arranged side by side. The two local regions A1 shown in Fig. 44 are the same, but the positions of the target pixels are different. In the local region A1 on the left side of Fig. 44, a low-density pixel adjacent to the edge boundary is the target pixel P11. As described above, the bilateral filter weights pixels adjacent to the target pixel according to a normal distribution, such that the weight decreases the further away the pixel is from the target pixel, and the weight decreases the greater the difference in pixel value between the pixel and the target pixel.

[0209] For this reason, the processing content derivation unit 86 determines the filter size of the bilateral filter based on the difference between the pixel value of the pixel of interest and the pixel values ​​of the pixels surrounding the pixel of interest. For example, the smaller the difference between the pixel value of the pixel of interest and the pixel values ​​of the pixels surrounding the pixel of interest, the larger the filter size is set. Furthermore, the processing content derivation unit 86 determines the weight of the bilateral filter based on the difference between the pixel value of the pixel of interest and the pixel values ​​of the pixels surrounding the pixel of interest. For example, the smaller the difference between the pixel value of the pixel of interest and the pixel values ​​of the pixels surrounding the pixel of interest, the larger the weight is set for pixels closer to the pixel of interest than for pixels farther from the pixel of interest.

[0210] As a result, the processing content derivation unit 86 derives a 3x3 bilateral filter F11 having weights as shown on the left side of Figure 44 as the processing content of the first graininess reduction processing for the pixel of interest P11 in the local area A1 on the left side of Figure 44.

[0211] In the local area A1 on the right side of Fig. 44, a high-density pixel adjacent to the edge boundary is the pixel of interest P12. Therefore, the processing content derivation unit 86 derives a 3 × 3 bilateral filter F12 having weights as shown on the right side of Fig. 44 as the processing content of the first graininess reduction processing for the pixel of interest P12 in the local area A1 on the right side of Fig. 44.

[0212] FIG. 45 is a diagram showing a local area A2 of a second radiographic image corresponding to the local area A1 of the first radiographic image shown in FIG. 44. FIG. 45 shows a local area A2 of 5 × 5 pixels near an edge included in the second radiographic image G2. The local area A2 is located in the same position as the local area A1 in the first radiographic image G1 shown in FIG. 44. The two local areas A2 shown in FIG. 45 are the same, but the positions of the target pixels are different. In the local area A2 on the left side of FIG. 45, the pixel corresponding to the target pixel P11 shown in the local area A1 on the left side of FIG. 44 is the target pixel P21. In the local area A2 on the right side of FIG. 45, the pixel corresponding to the target pixel P12 shown in the local area A1 on the right side of FIG. 44 is the target pixel P22.

[0213] Here, the second radiation detector 6 from which the second radiographic image G2 is acquired is irradiated with a lower dose of radiation than the first radiation detector 5 from which the first radiographic image G1 is acquired. Therefore, the second radiographic image G2 has more quantum noise from the radiation than the first radiographic image G1, resulting in poor granularity and indistinct edges. Furthermore, due to the influence of quantum noise, low-density pixels are contained in high-density regions near edge boundaries, and high-density pixels are contained in low-density regions. Therefore, it is not possible to appropriately determine a bilateral filter from the second radiographic image G2 that suppresses granularity while preserving edges, as was the case with the first radiographic image G1.

[0214] In this case, it is conceivable to use a smoothing filter such as a Gaussian filter, but such a smoothing filter cannot simultaneously suppress noise and preserve edges, resulting in the edges being buried in noise and making it impossible to restore the edges of structures contained in the second radiographic image G2.

[0215] For this reason, in the eighth embodiment, the processing content deriving unit 86 derives the processing content of the second graininess suppression processing for the second radiographic image based on the processing content of the first graininess suppression processing for the first radiographic image G1. That is, the processing content deriving unit 86 derives the processing content of the second graininess suppression processing so that the processing content of the second graininess suppression processing to be performed on each pixel of the second radiographic image G2 is the same as the processing content of the first graininess suppression processing to be performed on pixels of the first radiographic image G1 that correspond to each pixel of the second radiographic image G2. Specifically, the processing content deriving unit 86 derives, as the processing content of the second graininess suppression processing for the second radiographic image G2, a bilateral filter having the same size and the same weight as the bilateral filter determined for each pixel of the first radiographic image G1.

[0216] Fig. 46 is a diagram showing an example of a bilateral filter for the second radiographic image G2. Similar to Fig. 44, Fig. 46 also shows a local area A2 of 5 × 5 pixels near an edge included in the second radiographic image G2. As shown in Fig. 46, for a pixel of interest P21 in the local area A2 of the second radiographic image G2, the processing content derivation unit 86 derives, as processing content of the second graininess reduction processing, a bilateral filter F21 having the same size and weight as the bilateral filter F11 derived for the pixel of interest P11 in the local area A1 of the first radiographic image G1.

[0217] Furthermore, for the pixel of interest P22 in the local region A2 of the second radiographic image G2, the processing content derivation unit 86 derives, as the processing content of the second graininess suppression processing, a bilateral filter F22 having the same size and weight as the bilateral filter F12 derived for the pixel of interest P12 in the local region A1 of the first radiographic image G1.

[0218] In order to derive the processing details of the second graininess reduction processing, it is necessary to associate pixel positions between the first radiographic image G1 and the second radiographic image G2. For this reason, it is preferable to align the positions of the first radiographic image G1 and the second radiographic image G2.

[0219] The graininess reduction processing unit 87 performs graininess reduction processing on the first radiographic image G1 and the second radiographic image G2. That is, the graininess reduction processing is performed on the first radiographic image G1 and the second radiographic image G2 based on the processing content derived by the processing content derivation unit 86. Specifically, the graininess reduction processing unit 87 performs filtering processing on the first radiographic image G1 using the bilateral filter derived for the first radiographic image G1. Furthermore, the graininess reduction processing unit 87 performs filtering processing on the second radiographic image G2 using the bilateral filter derived based on the first radiographic image G1.

[0220] In the eighth embodiment, the subtraction unit 63 derives a bone image Gb using the first and second radiographic images G1 and G2 that have been subjected to graininess suppression processing according to the above formula (1). Then, the bone density deriving unit 64 derives the bone density B and a representative value of the bone density B of the target bone.

[0221] Next, a ninth embodiment of the present disclosure will be described. Fig. 47 is a diagram showing the functional configuration of an information derivation device according to the ninth embodiment. Note that in Fig. 47, the same components as those in Fig. 43 are assigned the same reference numerals, and detailed description thereof will be omitted. The information derivation device 50F according to the ninth embodiment of the present disclosure differs from the information derivation device 50E according to the eighth embodiment in that it further includes a map derivation unit 88 that derives a physical quantity map of the subject H based on at least one of the first radiographic image G1 and the second radiographic image G2, and the processing content derivation unit 86 derives processing content of the second graininess reduction processing for the second radiographic image G2 based on the physical quantity map.

[0222] The map derivation unit 88 derives a physical quantity map for the subject H. Examples of physical quantities include the body thickness and bone density of the subject H. The body thickness can be determined by using the body thickness distribution when the scattered radiation removal unit 62 satisfies the termination condition. The bone density can be determined by using the bone density derived by the bone density derivation unit 64.

[0223] Here, the contrast of the structures contained in the first and second radiographic images G1 and G2, which are the targets of graininess reduction processing, varies depending on the imaging conditions. Therefore, when edge-preserving smoothing processing is performed using a bilateral filter, it is necessary to control the intensity of the edges to be preserved depending on the imaging conditions. On the other hand, in the body thickness map representing the body thickness of the subject H, the contrast of the structures contained in the map is expressed by thickness (mm), which is independent of the imaging conditions.

[0224] For this reason, in the ninth embodiment, the processing content deriving unit 86 derives the processing content of the first graininess reduction processing for the first radiographic image G1 based on the physical quantity map. FIG. 48 is a diagram showing an example of a bilateral filter for the physical quantity map. Note that FIG. 48 shows two 5×5 pixel local regions A3 near an edge included in the physical quantity map, arranged side by side. The two local regions A3 shown in FIG. 48 are identical, but the positions of the target pixels are different. In the local region A3 on the left side of FIG. 48, a high-density pixel on the edge is the target pixel P31. For this reason, a 3×3 bilateral filter F31 having weights as shown on the left side of FIG. 48 is derived as the processing content of the first graininess reduction processing for the target pixel P31 of the local region A3 on the left side of FIG.

[0225] In the local area A3 on the right side of Fig. 48, a low-density pixel adjacent to the edge boundary is the pixel of interest P32. Therefore, for the pixel of interest P32 in the local area A3 on the right side of Fig. 48, a 3 × 3 bilateral filter F32 having weights as shown on the right side of Fig. 48 is derived as the processing content of the first graininess reduction processing.

[0226] In the ninth embodiment, the processing content derivation unit 86 also derives, as the processing content of the second graininess suppression processing for the second radiographic image G2, a bilateral filter identical to the bilateral filter determined for each pixel of the first radiographic image G1. That is, in the second radiographic image G2, in a local region corresponding to the local region A3 of the first radiographic image G1, a bilateral filter having the same size and weight as the bilateral filter F31 is derived as the processing content of the second graininess suppression processing for a pixel corresponding to the pixel of interest P31 in the local region A3. Furthermore, in the second radiographic image G2, a bilateral filter having the same size and weight as the bilateral filter F32 is derived as the processing content of the second graininess suppression processing for a pixel corresponding to the pixel of interest P32 in the local region A3 of the first radiographic image G1.

[0227] In the ninth embodiment, the graininess reduction processing unit 87 performs graininess reduction processing on the first radiographic image G1 and the second radiographic image G2 based on the processing content derived by the processing content derivation unit 86. The subtraction unit 63 derives a bone image Gb according to the above formula (1) using the first and second radiographic images G1 and G2 that have been subjected to the graininess reduction processing. The bone density derivation unit 64 then derives the bone density B and a representative value of the bone density B of the target bone.

[0228] The graininess suppression processing performed in the eighth and ninth embodiments may be performed in the first to seventh embodiments.

[0229] In addition, in each of the above embodiments, the bone density of the plain radiographic image G0 is estimated as information related to bone density, but this is not limited to this. For example, an evaluation value of fracture risk may be derived as an estimation result related to bone density. This will be described below as a tenth embodiment. The evaluation value of fracture risk can be derived, for example, using the method described in International Publication No. 2020 / 166561.

[0230] FIG. 49 is a diagram showing the functional configuration of an information derivation device according to the tenth embodiment. In FIG. 49, the same components as those in FIG. 7 are given the same reference numerals, and detailed description thereof will be omitted. In the tenth embodiment of the present disclosure, instead of deriving bone density as the correct answer data 42, an evaluation value of fracture risk is derived. For this reason, as shown in FIG. 49, an information derivation device 50G according to the tenth embodiment further includes a muscle mass derivation unit 110, a statistical value derivation unit 111, and an evaluation value derivation unit 112 in addition to the information derivation device 50 according to the first embodiment.

[0231] The subtraction unit 63 of the information derivation device 50G according to the tenth embodiment derives a soft tissue image Gs in which the soft tissue of the subject H is extracted from the first and second radiographic images G1 and G2, in addition to the bone image Gb. The soft tissue image Gs is derived using the following equation (28): In equation (25), β is a weighting coefficient for extracting the soft tissue. Gs(x, y)=G1(x, y)-β×G2(x, y) (28)

[0232] The muscle mass derivation unit 110 derives muscle mass for each pixel in the soft tissue region of the soft tissue image Gs based on the pixel value. Soft tissue includes muscle tissue, fatty tissue, blood, and water. In the muscle mass derivation unit 110 of the tenth embodiment, tissue in the soft tissue other than fatty tissue is considered to be muscle tissue. That is, in the muscle mass derivation unit 110 of the tenth embodiment, non-fatty tissue including blood and water is considered to be muscle tissue.

[0233] The muscle mass derivation unit 110 separates muscle from fat in the soft tissue image Gs by utilizing the difference in energy characteristics between muscle tissue and fat tissue. As shown in FIG. 50, the radiation dose after passing through the subject H, which is a human body, is lower than the radiation dose before entering the subject H. Furthermore, since muscle tissue and fat tissue absorb different energies and have different attenuation coefficients, the energy spectra of the radiation after passing through the muscle tissue and the radiation after passing through the fat tissue differ. As shown in FIG. 50, the energy spectrum of the radiation that passes through the subject H and is irradiated onto each of the first radiation detector 5 and the second radiation detector 6 depends on the body composition of the subject H, specifically, the ratio of muscle tissue to fat tissue. Because radiation is more easily transmitted through fat tissue than muscle tissue, the radiation dose after passing through the human body decreases when the ratio of muscle tissue to fat tissue is higher.

[0234] For this reason, the muscle mass derivation unit 110 separates muscle from fat from the soft tissue image Gs by utilizing the difference in energy characteristics between the muscle tissue and fat tissue described above. That is, the muscle mass derivation unit 110 generates a muscle image from the soft tissue image Gs. The muscle mass derivation unit 110 also derives the muscle mass of each pixel based on the pixel value of the muscle image.

[0235] The specific method by which the muscle mass derivation unit 110 separates muscle and fat from the soft tissue image Gs is not limited. As an example, the muscle mass derivation unit 110 of the tenth embodiment generates a muscle image from the soft tissue image Gs using the following equations (29) and (30). Specifically, the muscle mass derivation unit 110 first derives the muscle ratio rm(x, y) at each pixel position (x, y) in the soft tissue image Gs using equation (29). In equation (29), μm is a weighting coefficient corresponding to the attenuation coefficient of muscle tissue, and μf is a weighting coefficient corresponding to the attenuation coefficient of fat tissue. Δ(x, y) represents the density difference distribution. The density difference distribution is the distribution on the image of density changes as seen from the density obtained when radiation reaches the first radiation detector 5 and the second radiation detector 6 without passing through the subject H. The distribution of density changes on the image is calculated by subtracting the density of each pixel in the area of ​​the subject H from the density in the direct-pass area obtained by irradiating the first radiation detector 5 and the second radiation detector 6 with radiation in the soft tissue image Gs. rm(x,y)={μf-Δ(x,y) / T(x,y)} / (μf-μm) (29)

[0236] Furthermore, the muscle mass derivation unit 110 generates a muscle image Gm from the soft tissue image Gs using the following equation (30): In equation (30), x and y are the coordinates of each pixel in the muscle image Gm. Gm(x,y)=rm(x,y)×Gs(x,y) (30)

[0237] Then, the muscle mass derivation unit 110 multiplies each pixel (x, y) of the muscle image Gm by a coefficient C1(x, y) that represents the relationship between a predetermined pixel value and muscle mass, as shown in the following equation (31), to derive the muscle mass M(x, y) (g / cm) for each pixel of the muscle image Gm. 2 ) is derived. M(x,y)=C1(x,y)×Gm(x,y) (31)

[0238] The statistical value derivation unit 111 calculates a statistical value for the subject based on the bone density and muscle mass derived by the bone density derivation unit 64. As will be described later, the statistical value is used to calculate a fracture risk evaluation value for evaluating the fracture risk. Specifically, the statistical value derivation unit 111 derives a statistical value Q based on a bone density distribution index value Bd related to the spatial distribution of bone density and a muscle mass distribution index value Md related to the spatial distribution of muscle mass, as shown in the following equation (32). Q = W1 × Bd + W2 × Md (32)

[0239] W1 and W2 in equation (32) are weighting coefficients, which are determined by collecting a large number of bone density distribution index values ​​and muscle mass distribution index values ​​and performing regression analysis.

[0240] The bone density distribution index value is a value that represents how the bone density values ​​are spread out. Examples of the bone density distribution index value include the value per unit area of ​​bone density, the average value, the median value, the maximum value, and the minimum value. The muscle mass distribution index value is a value that represents how the muscle mass values ​​are spread out. Examples of the muscle mass distribution index value include the average value, the median value, the maximum value, and the minimum value of muscle mass.

[0241] Furthermore, the statistical value derivation unit 111 may obtain the statistical value Q based on at least one of the subject's height, weight, age, and fracture history, in addition to the bone density and muscle mass. For example, when obtaining the statistical value based on the bone density, muscle mass, and age, the statistical value Q is calculated by the following formula (33) based on the bone density distribution index value Bd, muscle mass distribution index value Md, and age Y. Q = W1 × Bd + W2 × Md + W3 × Y (33)

[0242] In equation (33), W1, W2, and W3 are weighting coefficients, and the weighting coefficients W1, W2, and W3 are determined by collecting a large amount of data on bone density distribution index values, muscle mass distribution index values, and the subject's ages corresponding to these index values, and performing regression analysis based on the data. Even when calculating statistical values ​​by adding the subject's height, weight, fracture history, and other factors in addition to age, it is preferable to multiply and add the weighting coefficients.

[0243] When using equation (33), if the weighting coefficients obtained by regression analysis based on a large amount of data are "W1 = 2.0, W2 = 0.1, W3 = -0.01", the bone density distribution index value Bd of a certain subject H is "1.0 g / cm 2 ", muscle mass distribution index value is "20 kg", and age Y is "40 years old", then the statistical value Q is "3.6" according to the following formula (34). Q=2.0×1.0+0.1×20+(-0.01)×40=3.6 (34)

[0244] The evaluation value derivation unit 112 calculates a fracture risk evaluation value for evaluating the fracture risk of the subject H based on the statistical value Q. Since the relationship between the statistical value Q and the fracture risk evaluation value is obtained from a large amount of diagnostic data, the evaluation value derivation unit 112 calculates the fracture risk evaluation value using this relationship. The relationship between the statistical value Q and the fracture risk evaluation value may be derived in advance and stored in the storage 53 as a table.

[0245] For example, the fracture risk evaluation value is the probability of fracture occurring within 10 years from the time of diagnosis of subject H (the time of acquisition of the first and second radiographic images G1 and G2). As described above, when formula (33) is used to calculate the statistical value Q and the weighting coefficients obtained by regression analysis based on a large amount of data are "W1=2.0, W2=0.1, W3=-0.01," the relationship between the "probability of fracture occurring within 10 years" and the "statistical value Q" is expressed as shown in Figure 51, such that the larger the statistical value Q, the lower the fracture probability.

[0246] In the tenth embodiment, the fracture risk assessment value derived by the information derivation device 50G is used as the correct answer data of the training data. Fig. 52 is a diagram showing the training data derived in the tenth embodiment. As shown in Fig. 52, the training data 40A consists of training data 41 including first and second radiographic images G1 and G2, and correct answer data 42A, which is the fracture risk assessment value.

[0247] By training a neural network using the training data 40A shown in Figure 52, a trained neural network 23A can be constructed that, when a simple radiographic image G0 is input, outputs a fracture risk assessment value as an estimated result related to bone density.

[0248] Next, an eleventh embodiment of the present disclosure will be described. FIG. 53 is a diagram showing the functional configuration of an information derivation device according to the eleventh embodiment. Note that in FIG. 53, the same components as those in FIG. 7 are assigned the same reference numerals, and detailed description thereof will be omitted. In the eleventh embodiment of the present disclosure, instead of deriving bone density as the correct answer data 42, information indicating the healing state of a bone portion after treatment is derived. For this purpose, as shown in FIG. 53, an information derivation device 50H according to the eleventh embodiment further includes a healing information derivation unit 114 in addition to the information derivation device 50 according to the first embodiment. Note that in the eleventh embodiment, it is assumed that surgery to implant an artificial object such as an artificial bone into the bone portion has been performed as the treatment of the bone portion.

[0249] The healing information derivation unit 114 derives, as healing information, information indicating the state of the bones of the subject after the artificial object has been implanted in the bones of the subject H, based on the bone density around the artificial object, such as an artificial bone, implanted in the bones of the subject H. Artificial objects, such as artificial bones, are implanted in a living body by surgery to replace bone lost due to a comminuted fracture, a tumor, or the like.

[0250] Fig. 54 is a diagram showing an example of an artificial bone embedded in the bone of a subject. Fig. 54 shows an example of the bone of subject H who has undergone total hip replacement surgery, with an artificial joint stem 131 embedded in the femur 130 of subject H.

[0251] Known methods for fixing the stem 131 include a direct fixation method (cementless fixation) and an indirect fixation method (cement fixation). In the direct fixation method, the stem 131 is inserted into a cavity inside the femur 130 without using cement. The cavity inside the femur 130 is shaped in advance so that the stem 131 fits into it. The surface of the stem 131 is roughened, and bone tissue grows by penetrating into the interior of the stem 131. That is, immediately after the stem 131 is embedded in the femur 130, a cavity exists between the stem 131 and the femur 130. However, as the femur 130 recovers, the cavity shrinks and disappears as the bone tissue grows. Therefore, by obtaining the bone density around the stem 131, it is possible to determine the degree of recovery of the femur 130 after surgery.

[0252] FIG. 55 is a graph showing an example of the relationship between the distance from the stem 131 inside the femur 130 and bone density at each postoperative stage. The horizontal axis of the graph shown in FIG. 55 represents the position along the line L in FIG. 54. In FIG. 55, the solid line corresponds to the initial stage immediately after the stem 131 is implanted in the femur 130, the dotted line corresponds to the intermediate recovery stage, and the dashed-dotted line corresponds to the complete recovery stage. As shown in FIG. 55, in the initial postoperative stage, the femur 130 and the stem 131 are not in close contact, and bone density near the stem 131 is extremely low. As recovery progresses, bone tissue grows and penetrates toward the inside of the stem 131, increasing bone density near the stem 131. Meanwhile, bone density at positions distal to the stem 131 remains substantially constant at each postoperative stage. At the complete recovery stage, bone density near the stem 131 and bone density at the distal position are substantially equal.

[0253] Hereinafter, a manner in which the healing information deriving unit 114 derives healing information will be described using an example in which a total hip replacement surgery shown in Figure 54 is performed. The healing information deriving unit 114 derives healing information from a position L A Bone mineral density in B Aand the position X, which is relatively far from the stem 131. B Bone mineral density in B B For example, the cure information deriving unit 114 derives a value ΔB according to the difference between the bone densities (ΔB=B B -B A ) may be derived as the healing information. In this case, the numerical value derived as the healing information decreases with recovery and approaches 0. In addition, the healing information deriving unit 114 may derive the ratio of bone densities (ΔB=B A / B B ) may be derived as healing information. In this case, the value ΔB derived as healing information increases as the bone recovers, approaching 1. That is, the bone density B A and B B The value ΔB corresponding to the difference between the values ​​is a value that indicates the degree of recovery of the bone portion after surgery. Therefore, by deriving the value ΔB as healing information, it is possible to quantitatively grasp the degree of recovery of the femur 130 after surgery.

[0254] The healing information derivation unit 114 derives healing information using the bone density B for each pixel of the bone image Gb derived by the bone density derivation unit 64. In each of the first radiographic image G1, the second radiographic image G2, and the bone image Gb, the pixel values ​​of the stem 131 are significantly different from the pixel values ​​in the bone region, so it is possible to identify the region in each of the above images where the stem 131 exists. Therefore, the healing information derivation unit 114 can identify the distance from the stem 131 based on any of the first radiographic image G1, the second radiographic image G2, and the bone image Gb.

[0255] FIG. 56 is a cross-sectional view showing an example of the cross-sectional structure of a human bone. As shown in FIG. 56, a human bone is composed of cancellous bone 140 and cortical bone 141 that covers the outside of the cancellous bone 140. The cortical bone 141 is harder and denser than the cancellous bone 140. The cancellous bone 140 is a collection of small bone pillars called trabeculae that extend within the marrow cavity. The trabeculae have a plate-like or rod-like structure and are interconnected. Because the bone density of the cancellous bone 140 and the bone density of the cortical bone 141 are significantly different, it is possible to distinguish between the cortical bone 141 and the cancellous bone 140 from the bone density B of each pixel in the bone image Gb.

[0256] When an artificial object is embedded in the cancellous bone 140, the healing information derivation unit 114 may identify the area of ​​the cancellous bone 140 based on the bone density B of each pixel of the bone image Gb, and derive healing information based on the bone density of the cancellous bone 140 around the artificial object. Specifically, the healing information derivation unit 114 may determine the position X A Bone mineral density in B A and position X in the cancellous bone 140, which is relatively far from the artificial object. B Bone mineral density in B B A numerical value ΔB corresponding to the difference between the values ​​may be derived as the cure information.

[0257] On the other hand, when an artificial object is embedded in the cortical bone 141, it is preferable that the healing information derivation unit 114 specifies the area of ​​the cortical bone 141 based on the bone density B of each pixel of the bone image Gb, and derives healing information based on the bone density of the cortical bone 141 around the artificial object. Specifically, the healing information derivation unit 114 derives healing information based on the bone density of the cortical bone 141 at a position X A Bone mineral density in B A and a position X in the cortical bone 141 that is relatively far from the artificial object. B To Bone density B B A numerical value ΔB corresponding to the difference between the values ​​may be derived as the cure information.

[0258] Furthermore, when an artificial object embedded in the bone portion of the subject H extends to both the cancellous bone 140 and the cortical bone 141, the regions of the cancellous bone 140 and the cortical bone 141 may be identified based on the bone density B of each pixel of the bone portion image Gb, and healing information may be derived based on the bone densities of both the cancellous bone 140 and the cortical bone 141 around the artificial object. Specifically, the healing information derivation unit 114 determines the position L in the cancellous bone 140 that is relatively close to the artificial object. A1 Bone mineral density in B A1 and a position L in the cancellous bone 140 that is relatively far from the artificial object. B1 Bone mineral density in B B1 A numerical value ΔB1 corresponding to the difference between the artificial object and the cortical bone 141 is derived as healing information, and a position L A2 Bone mineral density in B A2 and a position L in the cortical bone 141 that is relatively far from the artificial object. B2 Bone mineral density in B B2 A numerical value ΔB2 corresponding to the difference between the artificial object embedded in the bone portion of the subject H and the cancellous bone 140 may be derived as the healing information. When the artificial object embedded in the bone portion of the subject H extends to both the cancellous bone 140 and the cortical bone 141, the healing information may be derived based on the bone density of one of the cancellous bone 140 and the cortical bone 141 around the artificial object. In other words, one of the numerical values ​​ΔB1 and ΔB2 may be derived as the healing information.

[0259] In the 11th embodiment, the cure information derived by the information derivation device 50H according to the 11th embodiment is used as the correct answer data of the training data. Fig. 57 is a diagram showing the training data derived in the 11th embodiment. As shown in Fig. 57, the training data 40B consists of learning data 41 including the first and second radiographic images G1 and G2, and correct answer data 42B which is the numerical value of the cure information.

[0260] By training a neural network using the training data 40B shown in FIG. 57, it is possible to construct a trained neural network 23A that outputs information representing the healing state as healing information when a plain radiographic image G0 is input.

[0261] Next, an information derivation device according to a twelfth embodiment of the present disclosure will be described. Note that the configuration of the information derivation device according to the twelfth embodiment is the same as the configuration of the information derivation device according to the first embodiment, and only the processing performed by the scattered radiation removal unit 62 is different, so detailed description will be omitted here. Note that in the twelfth embodiment, first and second radiographic images G1 and G2 acquired by photographing a subject H using the imaging device 1A shown in Fig. 30, as in the sixth embodiment, are used as training data 40.

[0262] Fig. 58 is a diagram showing the functional configuration of a scattered radiation removal unit in the information derivation device according to the 12th embodiment. As shown in Fig. 58, the scattered radiation removal unit 62C in the information derivation device according to the 12th embodiment includes an area detection unit 150, a scattered radiation image derivation unit 151, a pixel value calculation unit 152, a pixel value replacement unit 153, a boundary position adjustment unit 154, and a calculation unit 155.

[0263] The region detection unit 150 obtains region detection images by detecting, in the first and second radiation images G1, G2, subject regions where radiation has passed through the subject H and reached the first and second radiation detectors 5, 6, and direct radiation regions where radiation has not passed through the subject H but has passed only through the tabletop 4A and directly reached the first and second radiation detectors 5, 6.

[0264] Specifically, as shown in Fig. 59, the region detection unit 150 detects a region in the first radiographic image G1 where the pixel value is less than the region threshold as the subject region 160, and detects a region in the first radiographic image G1 where the pixel value is equal to or greater than the region threshold as the direct radiation region 161. For example, if the region detection image is a binarized image in which the subject region 160 is set to "0" and the direct radiation region 161 is set to "1", a distribution such as that shown in Fig. 60 is obtained on a specific line 162 of the first radiographic image G1. Note that the region detection unit 150 may use a trained neural network that has been trained to detect the subject region and the direct radiation region, instead of using threshold processing for region detection.

[0265] The region threshold value is determined for each imaging condition, and it is preferable to use the region threshold value corresponding to the imaging condition when imaging the subject H. The region detection process may be performed on both the first radiographic image G1 and the second radiographic image G2, or on either one of them.

[0266] The scattered radiation image derivation unit 151 obtains a scattered radiation image relating to the scattered radiation component based on the region detection image and scattered radiation spread information relating to the spread of scattered radiation. The calculation unit 155 obtains a radiographic image from which the scattered radiation component has been removed by subtracting the scattered radiation image from the first and second radiographic images G1, G2. Note that the scattered radiation spread information used by the scattered radiation image derivation unit 151 may be, for example, that shown in FIG. 41.

[0267] The scattered radiation image derivation unit 151 then obtains a scattered radiation image containing scattered radiation components by convolving the region detection image with the PSF, ie, "region detection image * PSF (* is a convolution operator)." The scattered radiation image derivation unit 151 derives a scattered radiation image for each of the first radiographic image G1 and the second radiographic image G2.

[0268] In the scattered radiation image, the pixel values ​​of the scattered radiation components in the direct radiation region may be directly used as the pixel values ​​of the direct radiation region 161 of the first and second radiation images G1, G2, but the pixel values ​​of the direct radiation region 161 are often saturated (exceeding the pixel values ​​that the imaging sensors of the first and second radiation detectors 5, 6 can receive). For this reason, it is preferable to theoretically calculate, as the pixel values ​​of the direct radiation region of the scattered radiation image, non-saturated scattered radiation pixel values ​​that are not saturated and that take the influence of scattered rays into consideration, and to replace these theoretically calculated non-saturated scattered radiation pixel values ​​with the pixel values ​​of the direct radiation region of the scattered radiation image.

[0269] The pixel value calculation unit 152 calculates non-saturated scattered radiation pixel values ​​corresponding to the imaging dose by referring to a non-saturated scattered radiation pixel value relationship that indicates the relationship between the radiation dose and non-saturated scattered radiation pixel values, which are non-saturated pixel values ​​obtained when pixel values ​​are not saturated and the effects of scattered radiation are taken into consideration.The pixel value substitution unit 153 then substitutes pixel values ​​in the direct radiation region with non-saturated scattered radiation pixel values.Specifically, as shown in FIG. 61, in the scattered radiation image derived by the scattered radiation image derivation unit 151, pixel values ​​in the direct radiation region 161 are replaced with non-saturated scattered radiation pixel values ​​calculated by the pixel value calculation unit 152.

[0270] The non-saturated scattered radiation pixel value relations are predetermined for each imaging condition in a table (not shown) for the direct radiation region and stored in the storage 53. The pixel value calculation unit 152 refers to the table for the direct radiation region and uses one of the non-saturated scattered radiation pixel value relations corresponding to the imaging conditions when imaging the subject H, or uses a combination of multiple non-saturated scattered radiation pixel value relations that satisfy the imaging conditions when imaging the subject H. Furthermore, it is preferable to calculate the non-saturated scattered radiation pixel value by, for example, "non-saturated scattered radiation pixel value = non-saturated pixel value obtained when there is no pixel value saturation × scattered radiation content rate in the direct radiation region."

[0271] As described above, the region detection unit 150 distinguishes between the subject region 160 and the direct radiation region 161 using the region threshold value, but the direct radiation region 161 detected using the region threshold value may also include regions that have passed through soft tissue regions close to the skin of the subject H. If scattered radiation is also emitted from such soft tissue regions, subtracting the scattered radiation image from the first and second radiographic images G1, G2 will result in excessive removal of scattered radiation components. For this reason, the boundary position between the subject region 160 and the direct radiation region 161 can be adjusted by a specific width, and a scattered radiation image is obtained based on the region detection image after the boundary position adjustment and the scattered radiation spread information.

[0272] The boundary position adjustment unit 154 adjusts the boundary position between the subject region 160 and the direct radiation region 161 by a specific width. The boundary position is preferably adjusted when the pixel value of the direct radiation region exceeds a pixel value threshold value or when the radiation dose exceeds a dose threshold value. The specific width is preferably determined based on at least one of the body part of the subject H, the imaging method of the subject H, and the imaging conditions. The specific width is preferably determined based on pixel values ​​in the vicinity of the boundary position in the radiation image.

[0273] Specifically, when determining the specific width based on the shape of the part of the subject H, i.e., the body thickness distribution of the subject H, the specific width is set to a portion Px of the direct radiation region 161 detected using the region threshold value where the body thickness exceeds 0, as shown in the body thickness distribution of the specific line 162 portion in Figure 62. By adjusting the boundary position BP by the specific width corresponding to this portion Px, the subject region 160 expands by the specific width, while the direct radiation region 161 narrows by the specific width. Furthermore, when determining the specific width based on pixel values ​​near the boundary position, it is preferable to determine the specific width based on the inter-pixel distance between the pixel at the boundary position and a neighboring pixel that is within a specific range from the boundary position and has a pixel value within the specific range.

[0274] In the twelfth embodiment, the subtraction unit 63 derives a bone image Gb using the processed first and second radiographic images G1 and G2. Then, the bone density derivation unit 64 derives the bone density B and a representative value of the bone density B of the target bone using the bone image Gb derived by the subtraction unit 63.

[0275] The scattered radiation removal process according to the twelfth embodiment may be performed in the first to fifth and eighth to eleventh embodiments.

[0276] In the above-described embodiments, the first and second radiographic images G1 and G2 are used as the training data 41 of the training data 40, but this is not limiting. As shown in training data 40C in FIG. 63, a bone image Gb may be used as training data 41C instead of the second radiographic image G2. In this case, the bone image Gb may be derived by any of the first to eleventh embodiments. Furthermore, as shown in training data 40D in FIG. 64, a bone density image Gd, in which each pixel represents a bone density value, may be used as training data 41D instead of the second radiographic image G2. In this case, the bone density image Gd may have pixel values ​​that are the bone density values ​​derived by any of the first to twelfth embodiments.

[0277] In each of the above embodiments, a bone density image having pixel values ​​of the bone density B derived by the bone density deriving unit 64 may be used as the correct answer data 42 of the training data 40. In this case, the estimation unit 23 of the estimation device 10 derives the bone density image from the plain radiographic image G0 as an estimation result related to bone density. When the bone density image is derived in this way, the bone density image may be displayed on the display screen.

[0278] FIG. 65 is a diagram showing another example of a display screen for the estimation results. As shown in FIG. 65, the display screen 70A has an image display area 71 similar to the display screen 70 shown in FIG. 13. The image display area 71 displays a bone density image Gd, which is an estimation result of the bone density in the plain radiographic image G0 of the subject H. In the bone density image Gd, patterns are applied to the bone regions according to the bone density. Note that, for the sake of simplicity, in FIG. 65, patterns representing the bone mineral content are applied only to the femur. Below the image display area 71, a reference 73 indicating the magnitude of the bone mineral content for the applied pattern is displayed. The operator can easily recognize the patient's bone density by interpreting the bone mineral content image Gd while referring to the reference 73. Note that, instead of patterns, different colors may be applied to the bone mineral content image Gd according to the bone mineral content.

[0279] Although the above embodiments estimate information related to bone density of the femur near the hip joint, the bone to be estimated is not limited to the femur. The technology disclosed herein can also be applied to estimate information related to bone density of any bone, such as the femur and tibia near the knee joint, vertebrae such as the lumbar vertebrae, the calcaneus, and metacarpals.

[0280] In the above embodiments, bone density, fracture risk, and healing information are used as correct answer data included in the training data for training the neural network. Therefore, the bone density-related information estimated by the estimation unit 23 from the plain radiographic image G0 is, but is not limited to, the bone density, fracture risk, and healing information in the plain radiographic image G0. The trained neural network 23A may be constructed using the YAM, T-score, or Z-score as correct answer data, and the YAM, T-score, and Z-score may be estimated from the plain radiographic image G0 as bone density-related information. The estimation unit 23 may also use the detection results of the presence or absence of a fracture, tumor, or implant, or the osteoporosis assessment result, as the bone density-related information to be estimated. Furthermore, bone diseases related to bone density, such as multiple myeloma, rheumatism, arthropathy, and cartilage sclerosis, may be estimated as bone density-related information. In this case, the trained neural network 23A may be constructed using training data including such bone density-related information as correct answer data.

[0281] Furthermore, in the above-described embodiments, the first radiographic image G1 and the second radiographic image G2 themselves are used to derive bone density as ground truth data, but this is not limiting. For each pixel in the first radiographic image G1 and the second radiographic image G2, a moving average with surrounding pixels is calculated, and bone density may be derived using the first radiographic image G1 and the second radiographic image G2, with the moving average used as the pixel value of each pixel. Here, since cortical bone is important information in determining bone density, the moving average with surrounding pixels may be calculated for each pixel so as to maintain a resolution at which the cortical bone can be visually recognized, for example, a resolution of 2 mm or less at the actual size of the subject. In this case, the pixels used for the moving average may be appropriately determined based on information such as the distances between the radiation source 3, the subject H, and the radiation detectors 5 and 6, as well as information on the pixel sizes of the radiation detectors 5 and 6.

[0282] In each of the above embodiments, the trained neural network 23A is constructed by training the neural network in the estimation device 10, but this is not limiting. A trained neural network 23A constructed in a device other than the estimation device 10 may be used in the estimation unit 23 of the estimation device 10 in this embodiment.

[0283] Furthermore, in the above-described embodiments, when performing energy subtraction processing to derive bone density, the first and second radiographic images G1, G2 are acquired by a one-shot method, but this is not limited to this. The first and second radiographic images G1, G2 may also be acquired by a so-called two-shot method, in which imaging is performed twice using only one radiation detector. In the case of the two-shot method, the position of the subject H included in the first radiographic image G1 and the second radiographic image G2 may be shifted due to bodily movement of the subject H. For this reason, it is preferable to align the position of the subject in the first radiographic image G1 and the second radiographic image G2 before performing the processing of this embodiment.

[0284] The alignment process can be performed using, for example, the method described in Japanese Patent Laid-Open No. 2011-255060. The method described in Japanese Patent Laid-Open No. 2011-255060 generates a plurality of first band images and a plurality of second band images representing structures in different frequency bands for each of the first and second radiographic images G1 and G2, obtains the amount of misalignment between corresponding positions in the first band image and the second band image of the corresponding frequency band, and aligns the first radiographic image G1 and the second radiographic image G2 based on the amount of misalignment.

[0285] Furthermore, in the above-described embodiments, bone density is derived as the training data and information related to bone density is estimated using radiographic images acquired in a system that uses the first and second radiation detectors 5 and 6 to image the subject H. However, the technology of the present disclosure can also be applied to cases where the first and second radiographic images G1 and G2 are acquired using stimulable phosphor sheets instead of radiation detectors. In this case, two stimulable phosphor sheets are placed one on top of the other and irradiated with radiation that has passed through the subject H, and radiographic image information of the subject H is stored and recorded on each stimulable phosphor sheet. The radiographic image information is then photoelectrically read from each stimulable phosphor sheet to acquire the first and second radiographic images G1 and G2. The two-shot method may also be used when acquiring the first and second radiographic images G1 and G2 using stimulable phosphor sheets.

[0286] Furthermore, the radiation in the above embodiment is not particularly limited, and in addition to X-rays, α rays, γ rays, etc. can be used.

[0287] In the above embodiment, the following various processors can be used as the hardware structure of the processing units that perform various processes, such as the image acquisition unit 21, information acquisition unit 22, estimation unit 23, learning unit 24, and display control unit 25 of the estimation device 10, and the image acquisition unit 61, scattered radiation removal unit 62, subtraction unit 63, and bone density derivation unit 64 of the information derivation device 50, etc. As described above, the various processors include a CPU, which is a general-purpose processor that executes software (programs) and functions as various processing units, as well as a programmable logic device (PLD), which is a processor whose circuit configuration can be changed after manufacture, such as an FPGA (Field Programmable Gate Array), and an ASIC (Application Specific Integrated Circuit), which have a circuit configuration specifically designed to perform specific processes. It includes dedicated electrical circuits that are processors.

[0288] A single processing unit may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs or a combination of a CPU and an FPGA). Also, multiple processing units may be configured with a single processor.

[0289] Examples of multiple processing units configured in a single processor include, first, a configuration in which one processor is configured by combining one or more CPUs and software, as typified by client and server computers, and this processor functions as multiple processing units. Second, as typified by System on Chip (SoC), the functionality of an entire system including multiple processing units is realized in a single IC (Integrated Circuit) chip. In this way, the various processing units are configured as hardware structures using one or more of the various processors described above.

[0290] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements.

[0291] The following are appendices to the present disclosure. (Additional note 1) at least one processor; The processor: The neural network functions as a trained neural network that derives an estimation result related to the bone density of a bone portion from a simple radiographic image obtained by simply photographing a subject including the bone portion; The trained neural network is trained using, as training data, (i) two radiological images obtained by photographing a subject including a bone with radiation having different energy distributions, (ii) a radiological image of the subject and a bone image representing the bone of the subject, or (iii) a radiological image of the subject and a bone density image representing the bone density of the bone of the subject, and information related to the bone density of the bone of the subject. (Additional note 2) The bone mineral density-related information includes: a body thickness distribution of the subject estimated based on at least one of two radiographic images obtained by imaging the subject including bones and soft tissues using radiation having different energy distributions; The imaging conditions under which the two radiographic images were obtained, and The estimation device according to appendix 1, wherein the bone region is derived based on pixel values ​​of a bone region in a bone image from which the bone region is extracted, the pixel values ​​being derived by energy subtraction processing that performs weighted subtraction on the two radiographic images. (Additional note 3) The bone image is recognizing the bones and the soft tissue of the subject using at least one of the two radiographic images; deriving attenuation coefficients for the bones and the soft tissue using the recognition results of the bones and the soft tissue and the two radiographic images; The estimation device according to appended item 2, wherein the attenuation coefficient is derived by performing the energy subtraction process using the attenuation coefficient. (Additional note 4) The bone image is deriving a new weighting coefficient to be used in the weighted subtraction based on pixel values ​​of the bone portion included in the bone portion image; deriving a new bone image by performing the weighted subtraction on the two radiographic images using the new weighting coefficients; The estimation device according to appended claim 2, wherein the weighting coefficients are derived by repeatedly deriving new weighting coefficients based on the new bone image and deriving new bone images based on the new weighting coefficients. (Additional note 5) The bone image is deriving a difference between the value of (the attenuation coefficient of the soft tissue for each different energy distribution)×(the thickness of the soft tissue)+(the attenuation coefficient of the bone tissue for each different energy distribution)×(the thickness of the bone tissue) for each different energy distribution and each pixel value of the radiographic image, while changing the attenuation coefficient of the soft tissue for each different energy distribution, the thickness of the soft tissue, the attenuation coefficient of the bone tissue for each different energy distribution, and the thickness of the bone tissue; deriving the attenuation coefficient of the soft tissue and the attenuation coefficient of the bone for each of the different energy distributions, at which the difference is minimized or the difference is less than a predetermined threshold value; The estimation device according to appended claim 2, wherein the attenuation coefficient is derived by performing the energy subtraction process using a weighting coefficient derived based on the attenuation coefficient of the soft tissue and the attenuation coefficient of the bone tissue. (Additional note 6) The bone image is Deriving composition ratios of a plurality of compositions contained in the soft part of the subject; deriving an attenuation coefficient for each different energy distribution in the soft tissue for each pixel of the two radiographic images according to the composition ratio; The estimation device according to appendix 2, wherein the attenuation coefficient is derived by performing the energy subtraction process using a weighting coefficient derived based on the derived attenuation coefficient of the soft tissue and a predetermined attenuation coefficient of the bone tissue. (Additional note 7) The composition ratio is deriving a body thickness of the subject as a first body thickness and a second body thickness for each pixel in each of the two radiographic images; 7. The estimation device according to claim 6, wherein the first body thickness and the second body thickness are derived for each pixel of the radiographic image based on the first body thickness and the second body thickness. (Additional note 8) The composition ratio is deriving the first body thickness and the second body thickness based on the attenuation coefficient for each of the different energy distributions for each of the plurality of compositions; The estimation device described in Appendix 7 derives the first body thickness and the second body thickness while changing the thickness of the composition and the attenuation coefficient for each composition, and derives the first body thickness and the second body thickness based on the thickness of the composition at which the difference between the first body thickness and the second body thickness is equal to or less than a predetermined threshold. (Additional note 9) The bone image is The estimation device according to any one of appendixes 2 to 8, wherein a scattered ray removal process is performed to remove from the two radiographic images scattered ray components of the radiation irradiated onto the subject that are scattered by the subject, and the energy subtraction process is performed on the two radiographic images from which the scattered ray components have been removed. (Additional note 10) the scattered radiation removal process acquires radiation characteristics according to the body thickness distribution of an object interposed between the subject and a radiation detector that detects the radiation image; deriving a primary ray distribution and a scattered ray distribution of radiation contained in each of the two radiographic images using the imaging conditions, the body thickness distribution, and the radiation characteristics of the object; deriving an error between the sum of the primary ray distribution and the scattered ray distribution for each of the two radiographic images and the pixel value at each position of the two radiographic images, updating the body thickness distribution so that the error becomes less than a predetermined threshold, and repeatedly deriving the radiation characteristics based on the updated body thickness distribution and deriving the primary ray distribution and the scattered ray distribution contained in each of the two radiographic images; The estimation device according to appended item 9, wherein the scattered radiation distribution when the error is less than a predetermined threshold value is subtracted from each of the two radiographic images. (Additional note 11) the scattered radiation removal process derives a first primary ray distribution and a scattered ray distribution of the radiation that has passed through the subject using the two radiographic images; deriving a second primary ray distribution and a scattered ray distribution of the radiation that has passed through the object using the first primary ray distribution and the scattered ray distribution, and radiation characteristics of an object that is located between the subject and a radiation detector that detects the radiological image; The estimation device according to appended item 9, wherein the estimation is performed by deriving a radiation image after transmission through the subject and the object using the second primary ray distribution and scattered ray distribution. (Additional note 12) the scattered radiation removal process derives a region detection image by detecting, in the two radiographic images, a subject region where the radiation has passed through the subject and reached the radiation detection unit, and a direct radiation region where the radiation has directly reached the radiation detection unit without passing through the subject; deriving a scattered ray image relating to the scattered ray component based on the region detection image and scattered ray spread information relating to the spread of scattered rays; The estimation device according to appended item 9, wherein the estimation is performed by subtracting the scattered radiation image from the two radiographic images. (Additional note 13) The bone image is deriving processing details for a first graininess reduction process for a first radiographic image having a higher S / N ratio of the two radiographic images; deriving processing details of a second graininess reduction process for a second radiographic image having a low S / N ratio based on processing details of the first graininess reduction process; performing graininess reduction processing on the first radiographic image based on processing details of the first graininess reduction processing; performing graininess reduction processing on the second radiographic image based on the processing content of the second graininess reduction processing; 13. The estimation device according to any one of appendixes 2 to 12, wherein the estimation device is derived using the two radiographic images that have been subjected to the graininess reduction processing. (Additional note 14) The processing content of the first graininess suppression processing is as follows: The estimation device according to claim 13, wherein the physical quantity map of the subject is derived based on at least one of the first radiographic image and the second radiographic image. (Additional note 15) The estimation device according to any one of appendix 1 to 14, wherein the information related to bone density includes at least one of bone density, an evaluation value of the subject's fracture risk, and information representing the healing state of the bone portion after treatment. (Additional note 16) 1. An estimation method for deriving an estimation result related to bone density from a simple radiographic image obtained by simply photographing a subject including a bone portion, using a trained neural network that derives an estimation result related to bone density of the bone portion from the simple radiographic image, the method comprising: The trained neural network is trained using, as training data, (i) two radiological images obtained by photographing a subject including a bone with radiation having different energy distributions, (ii) a radiological image of the subject and a bone image representing the bone of the subject, or (iii) a radiological image of the subject and a bone density image representing the bone density of the bone of the subject, and information related to the bone density of the bone of the subject. (Additional note 17) an estimation program that causes a computer to execute a procedure for deriving an estimation result related to bone density from a plain radiographic image obtained by simple radiography of a subject including a bone portion, using a trained neural network that derives an estimation result related to bone density of the bone portion from the plain radiographic image, The trained neural network is an estimation program that is trained using, as training data, (i) two radiological images obtained by photographing a subject including a bone portion using radiation with different energy distributions, (ii) a radiological image of the subject and a bone portion image representing the bone portion of the subject, or (iii) a radiological image of the subject and a bone density image representing the bone density of the bone portion of the subject, and information related to the bone density of the bone portion of the subject. [Explanation of symbols]

[0292] 1. 1A Imaging Device 3 Radiation source 4. Photo stand 4A Top plate 4B Mounting part 5, 6 Radiation detector 7 Radiation Energy Conversion Filter 8 Anti-scatter grid 9. Image Storage System 10 Estimation device 11, 51 CPUs 12 Estimation Processing Program 12B Study Program 13, 53 Storage 14, 54 display 15, 55 Input devices 16, 56 memory 17, 57 Network I / F Buses 18 and 58 21 Image acquisition unit 22 Information Acquisition Department 23 Estimation part 23A Trained Neural Network 24 Learning Department 25 Display control unit 30 Neural Networks 31 Input layer 32 Middle Class 33 Output layer 35 convolutional layers 36 Pooling Layer 37 Fully connected layer 40, 40A, 40B, 40C, 40D training data 41, 41C, 41D Training data 42, 42A, 42B, 42C Correct data 47 Output Data 48 parameters 50,50A, 50B, 50C, 50D, 50E, 50G, 50H Information derivation device 52 Information derivation program 61 Image acquisition unit 62, 62A, 62B Scattered radiation removal section 63 Subtraction section 64 Bone density derivation section 65 Structure recognition part 66 Weighting coefficient derivation part 67 Initial weighting coefficient setting unit 68 Weighting coefficient derivation part 70, 70A display screen 71 Image display area 72 Bone density display area 73 References 81 Initial value derivation part 82 Attenuation coefficient derivation part 83 Weighting coefficient derivation part 84 Composition ratio derivation section 85 Attenuation coefficient setting section 86 Processing content derivation part 87 Grain suppression processing unit 88 Map derivation part 91 Shooting condition acquisition unit 92 Body thickness derivation part 93 Characteristics Acquisition Unit 94 Line distribution derivation part 95 Arithmetic section 97 First derivation part 98 Second derivation part 99 Image Generation Unit 101 Phantom 102 Lead plate 103 Air Layer 110 Muscle mass derivation section 111 Statistical Value Derivation Section 112 Evaluation value derivation unit 114 Cure Information Derivation Unit 120 PSF 121 Distribution of primary radiation components 122 Distribution of scattered radiation components 130 Femur 131 Stem 140 Cancellous bone 141 Cortical bone 150 Area detection unit 151 Scattered radiation image extraction unit 152 Pixel value calculation unit 153 Pixel value replacement unit 154 Boundary position adjustment section 155 Arithmetic section 160 Subject area 161 Direct radiation area 162 Specific Line A1~A3 local area BP boundary position C0 correction coefficient D1~D4 scatterers F11, F12, F21, F22, F31, F32 Bilateral Filters G0 plain radiographic image G1, G2 radiological images Gb Bone image Gd bone mineral density imaging K1~K3 Radiography images L distance LUT1~LUT9 tables P11, P12, P21, P22, P31, P32 Areas of interest Q Statistic Ra radiation

Claims

1. at least one processor; The processor: The neural network functions as a trained neural network that derives an estimation result related to the bone density of a bone portion from a simple radiographic image obtained by simply photographing a subject including the bone portion; The trained neural network is trained using, as training data, (i) two radiological images obtained by photographing a subject including a bone portion using radiation having different energy distributions, (ii) a radiological image of the subject and a bone portion image representing the bone portion of the subject, or (iii) a radiological image of the subject and a bone density image representing the bone density of the bone portion of the subject, and information related to the bone density of the bone portion of the subject.

2. The bone mineral density-related information includes: a body thickness distribution of the subject estimated based on at least one of two radiographic images obtained by imaging the subject including bones and soft tissues using radiation having different energy distributions; The imaging conditions under which the two radiographic images were obtained; and The estimation device according to claim 1 , wherein the bones are derived based on pixel values ​​of bone regions in the bone image from which the bones are extracted, the bones being derived by energy subtraction processing that performs weighted subtraction on the two radiographic images.

3. The bone image is recognizing the bones and the soft tissue of the subject using at least one of the two radiographic images; deriving attenuation coefficients for the bones and the soft tissue using the recognition results of the bones and the soft tissue and the two radiographic images; The estimation device according to claim 2 , wherein the attenuation coefficient is derived by performing the energy subtraction process using the attenuation coefficient.

4. The bone image is deriving a new weighting coefficient to be used in the weighted subtraction based on pixel values ​​of the bone portion included in the bone portion image; deriving a new bone image by performing the weighted subtraction on the two radiographic images using the new weighting coefficients; 3. The estimation device according to claim 2, wherein the weighting coefficients are derived by repeatedly deriving new weighting coefficients based on the new bone image and deriving new bone image based on the new weighting coefficients.

5. The bone image is deriving a difference between the value of (the attenuation coefficient of the soft tissue x the thickness of the soft tissue + the attenuation coefficient of the bone tissue x the thickness of the bone tissue) and each pixel value of the radiographic image for each different energy distribution while changing the attenuation coefficient for the soft tissue for each different energy distribution, the thickness of the soft tissue, the attenuation coefficient for the bone tissue for each different energy distribution, and the thickness of the bone tissue from initial values; deriving the attenuation coefficient of the soft tissue and the attenuation coefficient of the bone for each of the different energy distributions, at which the difference is minimized or the difference is less than a predetermined threshold value; The estimation device according to claim 2 , wherein the weighting coefficient is derived by performing the energy subtraction process using a weighting coefficient derived based on the attenuation coefficient of the soft tissue and the attenuation coefficient of the bone.

6. The bone image is Deriving composition ratios of a plurality of compositions contained in the soft part of the subject; deriving an attenuation coefficient for each different energy distribution in the soft tissue for each pixel of the two radiographic images according to the composition ratio; The estimation device according to claim 2 , wherein the attenuation coefficient is derived by performing the energy subtraction process using a weighting coefficient derived based on the derived attenuation coefficient of the soft tissue and a predetermined attenuation coefficient of the bone tissue.

7. The composition ratio is deriving a body thickness of the subject as a first body thickness and a second body thickness for each pixel in each of the two radiographic images; The estimation device according to claim 6 , wherein the thickness is derived for each pixel of the radiographic image based on the first body thickness and the second body thickness.

8. The composition ratio is deriving the first body thickness and the second body thickness based on the attenuation coefficient for each of the different energy distributions for each of the plurality of compositions; The estimation device described in claim 7, wherein the first body thickness and the second body thickness are derived while changing the thickness of the composition and the attenuation coefficient for each composition, and are derived based on the thickness of the composition at which the difference between the first body thickness and the second body thickness is equal to or less than a predetermined threshold value.

9. The bone image is 9. The estimation device according to claim 2, wherein a scattered ray removal process is performed to remove, from the two radiographic images, scattered ray components of radiation irradiated onto the subject that are scattered by the subject, and the energy subtraction process is performed on the two radiographic images from which the scattered ray components have been removed.

10. the scattered radiation removal process acquires radiation characteristics according to the body thickness distribution of an object interposed between the subject and a radiation detector that detects the radiation image; deriving a primary ray distribution and a scattered ray distribution of radiation contained in each of the two radiographic images using the imaging conditions, the body thickness distribution, and the radiation characteristics of the object; deriving an error between the sum of the primary ray distribution and the scattered ray distribution for each of the two radiographic images and the pixel value at each position of the two radiographic images, updating the body thickness distribution so that the error becomes less than a predetermined threshold value, and repeatedly deriving the radiation characteristics based on the updated body thickness distribution and deriving the primary ray distribution and the scattered ray distribution contained in each of the two radiographic images; The estimation device according to claim 9 , wherein the estimation is performed by subtracting the scattered radiation distribution when the error is less than a predetermined threshold value from each of the two radiographic images.

11. the scattered radiation removal process derives a first primary ray distribution and a scattered ray distribution of the radiation that has passed through the subject using the two radiographic images; deriving a second primary ray distribution and a scattered ray distribution of the radiation that has passed through the object using the first primary ray distribution and the scattered ray distribution, and radiation characteristics of an object that is located between the subject and a radiation detector that detects the radiological image; The estimation device according to claim 9 , wherein the estimation is performed by deriving a radiation image after transmission through the subject and the object using the second primary ray distribution and the scattered ray distribution.

12. the scattered radiation removal process derives a region detection image by detecting, in the two radiographic images, a subject region where the radiation has passed through the subject and reached the radiation detection unit, and a direct radiation region where the radiation has directly reached the radiation detection unit without passing through the subject; deriving a scattered ray image relating to the scattered ray component based on the region detection image and scattered ray spread information relating to the spread of scattered rays; The estimation device according to claim 9 , wherein the estimation is performed by subtracting the scattered radiation image from the two radiographic images.

13. The bone image is deriving processing details for a first graininess reduction process for a first radiographic image having a higher S / N ratio of the two radiographic images; deriving processing details of a second graininess reduction process for a second radiographic image having a low S / N ratio based on processing details of the first graininess reduction process; performing graininess reduction processing on the first radiographic image based on processing details of the first graininess reduction processing; performing graininess reduction processing on the second radiographic image based on processing details of the second graininess reduction processing; The estimation device according to claim 2 , wherein the estimation is derived using the two radiographic images that have been subjected to the graininess reduction processing.

14. The processing content of the first graininess suppression processing is as follows: The estimation device according to claim 13 , wherein the estimation value is derived based on a physical quantity map of the subject derived based on at least one of the first radiographic image and the second radiographic image.

15. The estimation device according to claim 1 , wherein the information related to bone density includes at least one of bone density, an evaluation value of the subject's fracture risk, and information indicating a healing state of the bone portion after treatment.

16. 1. An estimation method for deriving an estimation result related to bone density from a simple radiographic image obtained by simply photographing a subject including a bone portion, using a trained neural network that derives an estimation result related to bone density of the bone portion from the simple radiographic image, the method comprising: the trained neural network is trained using, as training data, (i) two radiological images obtained by photographing a subject including a bone portion using radiation having different energy distributions, (ii) a radiological image of the subject and a bone portion image representing the bone portion of the subject, or (iii) a radiological image of the subject and a bone density image representing the bone density of the bone portion of the subject, and information related to the bone density of the bone portion of the subject.

17. an estimation program that causes a computer to execute a procedure for deriving an estimation result related to bone density from a plain radiographic image obtained by simple radiography of a subject including a bone portion, using a trained neural network that derives an estimation result related to bone density of the bone portion from the plain radiographic image, The trained neural network is an estimation program that is trained using, as training data, (i) two radiological images obtained by photographing a subject including a bone portion using radiation with different energy distributions, (ii) a radiological image of the subject and a bone portion image representing the bone portion of the subject, or (iii) a radiological image of the subject and a bone density image representing the bone density of the bone portion of the subject, and information related to the bone density of the bone portion of the subject.

Images