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 or a DXA scan image acquired by imaging the subject by a DXA method. The learned neural network is learned by using, as teacher data, a composite two-dimensional image showing the subject derived by composing three-dimensional CT images of the subject, and information related to the bone density 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. In DXA, radiation that enters and penetrates the human body has an attenuation coefficient μ (cm 2 / g) and its density ρ(g / cm 3 This is a method to calculate bone mineral density from the pixel values ​​of radiographic images taken with two types of radiation energy, taking advantage of the attenuation characterized by the radiation energy (cm) and thickness (t) of the bone.

[0003] Also, various methods for evaluating bone density using a radiographic image obtained by photographing a subject have been proposed. For example, Patent Documents 1 and 2 propose a method for estimating information related to bone density from an image showing bones by using a trained neural network constructed by training a neural network. In the method described in Patent Document 1, a neural network is trained using images showing bones and bone density obtained by simple radiography as training data. In addition, in the method described in Patent Document 1, a neural network is trained using images showing bones obtained 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 radiation image obtained by plain radiography will be referred to as a plain radiation 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 method for estimating bone density with even higher accuracy.

[0007] The present disclosure has been made in consideration of the above circumstances, and has an object to make it possible to estimate bone density with high accuracy. [Means for solving the problem]

[0008] The present disclosure provides an estimation apparatus comprising 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 plainly photographing a subject including a bone portion or a DXA scanned image obtained by photographing the subject using a DXA method; The trained neural network is trained using a synthetic two-dimensional image representing the subject derived by synthesizing three-dimensional CT images of the subject and information related to the bone density of the subject as training data.

[0009] In addition, in the estimation device according to the present disclosure, the composite two-dimensional image may be derived by deriving the radiation attenuation coefficient for a composition at each position in three-dimensional space, and projecting a CT image in a predetermined direction based on the attenuation coefficient.

[0010] In addition, in the estimation device according to the present disclosure, information related to bone density may be derived by identifying a bone region in a CT image, deriving an attenuation coefficient of radiation in the bone region, and deriving bone density at each position in the bone region based on the attenuation coefficient of radiation and the mass attenuation coefficient in the bone region.

[0011] In addition, in the estimation device according to the present disclosure, information related to bone density may be derived by projecting the bone density at each position in the bone region in a predetermined direction.

[0012] 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 per unit area, bone density per unit volume, an assessment value of the subject's fracture risk, and information representing the healing state of the bone after treatment.

[0013] In the estimation device according to the present disclosure, the processor functions as a trained neural network that derives an estimation result related to bone mineral density of the bone portion from the DXA scan image, The trained neural network may be trained using a low-resolution composite two-dimensional image obtained by processing the composite two-dimensional image to reduce its resolution and information related to the bone density of the subject as training data.

[0014] Furthermore, in the estimation device according to the present disclosure, the low-resolution composite 2D image is an image in which the pixel value of multiple adjacent pixels of the composite 2D image is the average value of the pixel values ​​of the multiple adjacent pixels, and the size of the multiple adjacent pixels may correspond to the size of one pixel of the DXA scan image.

[0015] In addition, in the estimation device according to the present disclosure, the low-resolution composite two-dimensional image may be an image obtained by performing moving average processing in one direction of the composite two-dimensional image, and the one direction may correspond to the scanning direction of the DXA scan image.

[0016] Furthermore, in the estimation device according to the present disclosure, the low-resolution composite 2D image is an image generated by generating a first low-resolution image in which the pixel value of adjacent pixels in the composite 2D image is the average value of the pixel values ​​of the adjacent pixels, and performing a moving average process in one direction on the first low-resolution image, wherein the size of the adjacent pixels corresponds to the size of one pixel of the DXA scan image, and the one direction corresponds to the scanning direction of the DXA scan image.

[0017] The estimation method according to the present disclosure is a method for deriving an estimation result related to bone density from a plain radiographic image or a DXA scanned image by using a trained neural network that derives an estimation result related to bone density from a plain radiographic image obtained by simply photographing a subject including a bone or a DXA scanned image obtained by photographing the subject using a DXA method, the method comprising: The trained neural network is trained using a synthetic two-dimensional image representing the subject derived by synthesizing three-dimensional CT images of the subject and information related to the bone density of the subject as training data.

[0018] The estimation method according to the present disclosure may be provided as a program for causing a computer to execute the method. Effect of the Invention

[0019] According to the present disclosure, bone density can be estimated with high accuracy. [Brief description of the drawings]

[0020] [Figure 1] FIG. 1 is a schematic block diagram showing a configuration of a radiation image capturing system to which an estimation device according to a first embodiment of the present disclosure is applied; [Diagram 2] FIG. 1 is a diagram showing a schematic configuration of an estimation device according to a first embodiment. [Diagram 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 the present embodiment; [Diagram 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] FIG. 1 is a diagram for explaining derivation of a synthetic two-dimensional image. [Figure 9] FIG. 1 is a diagram for explaining derivation of a synthetic two-dimensional image. [Figure 10] Diagram to explain CT value [Figure 11] A diagram showing the relationship between radiation energy and mass attenuation coefficient [Figure 12] Diagram to explain neural network learning [Figure 13] Conceptual diagram of the processing performed by a trained neural network [Figure 14] A diagram showing the display screen of the estimation results [Figure 15] 1 is a flowchart of a learning process performed in the first embodiment. [Figure 16] 1 is a flowchart of an estimation process performed in the first embodiment. [Figure 17] Another example of training data [Figure 18] FIG. 13 is a diagram showing a functional configuration of an information derivation device according to a second embodiment. [Figure 19] Graph showing the relationship between statistics and the probability of fracture within 10 years [Figure 20] Another example of training data [Figure 21] FIG. 13 is a diagram showing a functional configuration of an information derivation device according to a third embodiment. [Figure 22] A diagram showing an example of an artificial bone embedded in a bone part of a subject. [Diagram 23] Graph showing an example of the relationship between the distance from the stem inside the femur and the bone mineral content at each postoperative stage. [Figure 24] A cross-sectional view showing an example of the cross-sectional structure of a human bone [Diagram 25] Another example of training data [Figure 26] FIG. 13 is a diagram showing another example of a display screen for the estimation result. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0021] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. Fig. 1 is a schematic block diagram showing a 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, a CT device 7, 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 CT (Computed Tomography) device 7, the estimation device 10, and the information derivation device 50 are connected to the image storage system 9 via a network (not shown).

[0022] The imaging device 1 is an imaging device capable of acquiring a simple radiological image G0 of the subject H by irradiating a radiation detector 5 with radiation such as X-rays that is emitted from a radiation source 3 and passes through the subject H. The acquired simple radiological image G0 is input to the estimation device 10. The simple radiological image G0 is, for example, a front image including the crotch area of ​​the subject H.

[0023] The radiation detector 5 is capable of repeatedly recording and reading out radiation images, and may be a so-called direct type radiation detector that generates electric charges by directly receiving radiation, or a so-called indirect type radiation detector that converts radiation into visible light and then converts the visible light into an electric charge signal. As a method for reading out the radiation image signal, it is preferable to use a so-called TFT readout method in which the radiation image signal is read out by turning on and off a TFT (thin film transistor) switch, or a so-called optical readout method in which the radiation image signal is read out by irradiating it with readout light, but this is not limiting and other methods may also be used.

[0024] The CT device 7 obtains a plurality of tomographic images representing a plurality of tomographic planes in the subject H as a three-dimensional CT image V0. The CT value of each pixel (voxel) in the CT image is a numerical representation of the radiation absorption rate in the components that make up the human body. The CT value will be described later.

[0025] The image storage system 9 is a system that stores image data of radiographic images acquired by the imaging device 1 and image data of CT images acquired by the CT device 7. The image storage system 9 extracts images from the stored radiographic images and CT images in response to requests from the estimation device 10 and the information derivation device 50, and transmits the images to the requesting device. A specific example of the image storage system 9 is a PACS (Picture Archiving and Communication System). 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.

[0026] Next, an estimation device according to a first embodiment will be described. First, a hardware configuration of the estimation device according to the first embodiment will be described with reference to FIG. 2. 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, a non-volatile storage 13, and a 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.

[0027] 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.

[0028] The estimation program 12A and the learning program 12B are stored in a storage device of a server computer connected to a network or in a network storage in an externally accessible state, and are downloaded and installed in the computer constituting the estimation device 10 upon request. 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 in the computer constituting the estimation device 10 from the recording medium.

[0029] Next, a 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.

[0030] The image acquiring unit 21 causes the imaging device 1 to perform simple imaging of the subject H, thereby acquiring from the radiation detector 5 a simple radiation image G0 which is, for example, a front image of the crotch area of ​​the subject H. When acquiring the simple radiation image G0, imaging conditions are set, 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 surface of the radiation detector 5, 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.

[0031] The imaging conditions may be set by the operator through input from the input device 15. The set imaging conditions are stored in the storage 13. The plain radiographic image G0 and the imaging conditions are also transmitted to the image storage system 9 and stored therein.

[0032] In this embodiment, 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 simple radiographic image G0 stored in the storage 13 by reading it out from the storage 13 for processing.

[0033] The information acquisition unit 22 acquires teacher data for training a neural network, which will be described later, from the image storage system 9 via the network I / F 17.

[0034] The estimation unit 23 derives an estimation result related to the bone density of the bone part 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 part region included in the simple radiographic image G0. For this purpose, 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.

[0035] The learning unit 24 constructs a trained neural network 23A by machine learning the neural network using the teacher data. Examples of the neural network 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.

[0036] 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 convolution layers 35, a plurality of pooling layers 36, and a fully connected layer 37. In the neural network 30, the fully connected layer 37 exists in front of the output layer 33. In the neural network 30, the convolution layers 35 and the pooling layers 36 are alternately arranged between the input layer 31 and the fully connected layer 37.

[0037] 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 convolution layer 35 and one pooling layer 36 between the input layer 31 and the fully connected layer 37.

[0038] 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 is composed of training data 41 and correct answer data 42. In this embodiment, the data input to trained neural network 23A to obtain an estimation result of bone density is a plain radiographic image G0, while training data 41 includes a composite two-dimensional image C0 representing subject H derived by combining with a CT image V0.

[0039] The correct answer data 42 is the bone density of the target bone (i.e., the 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 synthetic two-dimensional image C0, which is the learning data 41, and the bone density, which is the correct answer data 42, are derived by the information derivation device 50. The bone density, which is the correct answer data 42, is an example of information related to the bone density of the bone part of the subject. The information derivation device 50 will be described below.

[0040] 6 is a schematic block diagram showing the configuration of the information derivation device according to the first embodiment. As shown in FIG. 6, the 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, a non-volatile storage 53, and a memory 56 as a temporary storage area. The information derivation device 50 also includes a display 54 such as a liquid crystal display, an input device 55 consisting of a pointing device such as a keyboard and a mouse, and a network I / F 57 connected to a network (not shown). The CPU 51, the storage 53, the display 54, the input device 55, the memory 56, and the network I / F 57 are connected to a bus 58.

[0041] 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 out the information derivation program 52 from the storage 53, expands it in the memory 56, and executes the expanded information derivation program 52.

[0042] Next, a 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 synthesis unit 62, and a bone density derivation unit 63. When the CPU 51 executes the information derivation program 52, the CPU 51 functions as the image acquisition unit 61, the synthesis unit 62, and the bone density derivation unit 63.

[0043] The image acquisition unit 61 acquires a CT image V0 for deriving the learning data 41 from the image storage system 9. Note that the image acquisition unit 61 may acquire the CT image V0 by having the CT device 7 capture an image of the subject H, similar to the image acquisition unit 21 of the estimation device 10.

[0044] The synthesis unit 62 synthesizes the CT images V0 to derive a synthetic two-dimensional image C0 representing the subject H. FIG. 8 is a diagram for explaining the derivation of the synthetic two-dimensional image C0. Note that in FIG. 8, the three-dimensional CT image V0 is shown in two dimensions for the sake of explanation. As shown in FIG. 8, the subject H is included in the three-dimensional space represented by the CT image V0. The subject H is composed of multiple components, such as bones, fat, muscles, and internal organs.

[0045] Here, the CT value V0(x, y, z) of each pixel of the CT image V0 can be expressed by the following formula (1) using the attenuation coefficient μi of the composition at that pixel and the attenuation coefficient μw of water. (x, y, z) are coordinates that represent the pixel position of the CT image V0. In the following explanation, the attenuation coefficient means the radiation source attenuation coefficient unless otherwise specified. The attenuation coefficient represents the degree (proportion) of attenuation of radiation due to absorption or scattering, etc. The attenuation coefficient differs depending on the specific composition (density, etc.) and thickness (mass) of the structure through which the radiation passes. V0(x,y,z)=(μi-μw) / μw×1000 (1)

[0046] The attenuation coefficient μw of water is known. Therefore, by solving equation (1) for μi, the attenuation coefficient μi of each composition can be calculated as shown in equation (2) below. μi=V0(x,y,z)×μw / 1000+μw (2)

[0047] As shown in FIG. 8, the synthesis unit 62 virtually irradiates the subject H with radiation of an exposure dose I0, and derives a synthetic two-dimensional image C0 by virtually detecting the radiation transmitted through the subject H by a radiation detector (not shown) installed on a virtual plane 64. The exposure dose I0 and radiation energy of the virtual radiation are set according to predetermined imaging conditions. Specifically, the incident dose I0 may be set by referring to a table prepared according to imaging conditions such as tube voltage, mAs value, and SID. Also, the radiation energy may be set by referring to a table prepared according to the tube voltage. At this time, the reaching dose I1(x,y) for each pixel of the synthetic two-dimensional image C0 passes through one or more compositions in the subject H. Therefore, the reaching dose I1(x,y) can be derived by the following formula (3) using the attenuation coefficient μi of one or more compositions through which the radiation of the exposure dose I0 passes. The reaching dose I1(x,y) becomes the pixel value of each pixel of the synthetic two-dimensional image C0. I1(x,y)=I0×exp(-∫μi·dt) (3)

[0048] If the irradiating radiation source is assumed to be a surface light source, the attenuation coefficient μi used in equation (3) may be derived from equation (2) using the CT values ​​of the pixels arranged in the vertical direction as shown in Fig. 8. If the irradiating radiation source is assumed to be a surface light source, as shown in Fig. 9, pixels on the path of the radiation that reaches each pixel may be identified based on the geometrical positional relationship between the point light source and each position on a virtual plane 64, and the attenuation coefficient μi derived from the CT value of the identified pixel using equation (2) may be used.

[0049] The bone density derivation unit 63 uses the CT image V0 to derive the bone density of the subject H for each pixel of the composite two-dimensional image C0. Here, the CT value will be explained. FIG. 10 is a diagram for explaining the CT value. The CT value is a numerical representation of the X-ray absorption rate in the human body. Specifically, as shown in FIG. 10, the CT value is determined according to the composition of the human body, such that water has a CT value of 0 and air has a CT value of -1000 (unit: HU).

[0050] The bone density derivation unit 63 first identifies a bone region in the CT image V0 based on the CT value of the CT image V0. Specifically, a region consisting of pixels with a CT value of 100 to 1000 is identified as the bone region by threshold processing. Note that instead of threshold processing, the bone region may be identified by using a trained neural network that has been trained to detect the bone region from the CT image V0. Alternatively, the CT image V0 may be displayed on the display 54, and the bone region may be identified by accepting a manual designation of the bone region in the displayed CT image V0.

[0051] Here, the density per unit volume of the composition at each pixel of the CT image is ρ [g / cm 3 ] is the attenuation coefficient μi[1 / cm] of the composition and the mass attenuation coefficient μe[cm] of the composition 2 / g] according to the following formula (4). ρ=μi / μe (4)

[0052] FIG. 11 is a diagram showing the relationship between radiation energy and mass attenuation coefficient for various compositions of the human body. FIG. 11 shows the relationship between radiation energy and mass attenuation coefficient for bones, muscles, etc., and fat. Note that muscles, etc. refer to muscles, blood, and water. In this embodiment, the relationship between radiation energy and mass attenuation coefficient shown in FIG. 11 is stored in the storage 53 as a table. In this embodiment, since the mass attenuation coefficient of bones is required, the mass attenuation coefficient of bones is obtained by referring to the relationship for bones in the table shown in FIG. 11 based on virtual radiation energy. In addition, the attenuation coefficient μb in each pixel of the bone region is derived by the above formula (2). Then, the bone density ρ per unit volume in each pixel of the bone region included in the CT image V0 is derived by the above formula (4).

[0053] Since the CT image V0 is a three-dimensional image, the unit of bone density per unit volume derived by the above formula (4) is [g / cm 3 In this embodiment, the bone density derivation unit 63 derives the bone density per unit area for each pixel of the composite two-dimensional image C0. For this reason, the bone density derivation unit 63 projects the bone density per unit volume ρ derived by the above formula (4) onto a virtual plane 64 in the same manner as when the composite two-dimensional image C0 is derived, thereby deriving the bone density per unit area B [g / cm 2 ] is derived.

[0054] In addition, when projecting, a representative value of bone density of each pixel of the CT image V0 on a path from the virtual radiation source to each pixel of the composite two-dimensional image C0 may be derived. The representative value may be an integrated value, an average value, a maximum value, a median value, a minimum value, or the like. Furthermore, in this embodiment, the bone density deriving unit 63 may derive a representative value of bone density only for the target bone. For example, when the target bone is the femur, the bone density deriving unit 63 derives a representative value of bone density of the femur region by deriving a representative value of bone density of each pixel in the femur region in the composite two-dimensional image C0. 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.

[0055] The bone density used as the supervised data 42 is derived at the same time as the learning data 41 is acquired, and is transmitted to the image storage system 9. In the image storage system 9, the learning data 41 and the supervised data 42 are associated with each other and stored as the teacher data 40. Note that, in order to improve the robustness of learning, teacher data 40 including images obtained by performing at least one of the following on the same image, such as enlarging / reducing, changing the contrast, moving, rotating in a plane, inverting, and adding noise, may be additionally created and stored as the learning data 41.

[0056] Returning to the estimation device 10, the learning unit 24 learns the neural network using a large amount of teacher data 40. FIG. 12 is a diagram for explaining the learning of the neural network 30. When learning the neural network 30, the learning unit 24 inputs learning data 41, i.e., a synthetic two-dimensional image C0, to the input layer 31 of the neural network 30. Then, the learning unit 24 causes the output layer 33 of the neural network 30 to output the bone density of the target bone as output data 47. Then, the learning unit 24 derives the difference between the output data 47 and the ground truth data 42 as a loss L0.

[0057] The learning unit 24 learns the neural network 30 based on the loss L0. Specifically, the learning unit 24 adjusts the kernel coefficients in the convolution layer 35, the connection weights between the layers, and the connection weights in the fully connected layer 37 (hereinafter referred to as parameters 48) so as to reduce the loss L0. For example, the backpropagation method can be used as a method for adjusting the parameters 48. The learning unit 24 repeats the adjustment of the parameters 48 until the loss L0 becomes equal to or less than a predetermined threshold value. As a result, when a plain radiographic image G0 is input, the parameters 48 are adjusted so as to output the bone density of the target bone, and the trained neural network 23A is constructed. The constructed trained neural network 23A is stored in the storage 13.

[0058] Fig. 13 is a conceptual diagram of the process performed by the trained neural network 23A. As shown in Fig. 13, when a simple 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 simple radiographic image G0.

[0059] The display control unit 25 displays the bone density estimation result estimated by the estimation unit 23 on the display 14. Fig. 14 is a diagram showing a display screen of the estimation result. As shown in Fig. 14, 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 in the bone density estimated by the estimation unit 23 is displayed in the bone density display area 72.

[0060] Next, the process performed in the first embodiment will be described. FIG. 15 is a flowchart showing the learning process performed in the first embodiment. First, the information acquisition unit 22 acquires the teacher data 40 from the image storage system 9 (step ST1), and the learning unit 24 inputs the learning data 41 included in the teacher data 40 to the neural network 30 to output the bone density, and learns the neural network 30 using the loss L0 based on the difference from the correct answer data 42 (step ST2), and returns to step ST1. Then, the learning unit 24 repeats the processes of steps ST1 and ST2 until the loss L0 becomes a predetermined threshold value, and ends the learning process. Note that the learning unit 24 may end the learning process by repeating the learning a predetermined number of times. In this way, the learning unit 24 constructs a trained neural network 23A.

[0061] Next, the estimation process in the first embodiment will be described. FIG. 16 is a flowchart showing the estimation process in the first embodiment. It is assumed that the simple radiographic image G0 is acquired by imaging 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 together with the simple radiographic image G0 on the display 14 (step ST13), and the process ends.

[0062] In this manner, 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 learning using the composite two-dimensional image C0 derived from the CT image V0 and the bone density derived from the CT image V0 as teacher data. Here, in this embodiment, the composite two-dimensional image C0 derived from the CT image V0 and the bone density derived from the CT image V0 are used for training the neural network. Therefore, compared to a case where one radiographic image and information related to bone density derived from the radiographic image are used as teacher data, the trained neural network 23A can derive an estimation result related to bone density more accurately from the simple radiographic image G0. Therefore, according to this embodiment, an estimation result related to bone density can be derived more accurately.

[0063] In the first embodiment, the bone density per unit area is derived as the correct answer data 42, but the present invention is not limited to this. In the first embodiment, the bone density per unit volume obtained in the process of deriving the bone density per unit area may be derived as the correct answer data. The bone density per unit volume may be a representative value of the bone density in the pixels in the region of the target bone in the CT image V0. The representative value may be an average value, a median value, a minimum value, a maximum value, or the like. The teacher data in this case is shown in FIG. 17. As shown in FIG. 17, the teacher data 40A is composed of learning data 41 including the composite two-dimensional image C0 and correct answer data 42A which is the bone density per unit volume.

[0064] By training a neural network using the training data 40A shown in FIG. 17, it is possible to construct a trained neural network 23A that, when a simple radiographic image G0 is input, outputs bone density per unit volume as an estimated result related to bone density.

[0065] In addition, in each of the above-mentioned embodiments, the bone density per unit area or per unit volume of the plain radiographic image G0 is estimated as the information related to the bone density, but the present invention is not limited to this. For example, an evaluation value of the fracture risk may be derived as an estimated result related to the bone density. This will be described below as a second embodiment.

[0066] Fig. 18 is a diagram showing a functional configuration of an information derivation device according to a second embodiment. In Fig. 18, the same components as those in Fig. 7 are given the same reference numbers, and detailed description will be omitted. In the second embodiment of the present disclosure, instead of deriving bone density, an evaluation value of a fracture risk is derived as correct answer data 42. For this reason, as shown in Fig. 18, an information derivation device 50A according to the second embodiment further includes a muscle density derivation unit 65, a statistical value derivation unit 66, and an evaluation value derivation unit 67 in addition to the information derivation device 50 according to the first embodiment.

[0067] The muscle density derivation unit 65 identifies muscle regions based on the CT value in the CT image V0. Specifically, a region consisting of pixels with a CT value of 60 to 70 is identified as a muscle region by threshold processing. Note that instead of threshold processing, a trained neural network that has been trained to detect muscle regions from the CT image V0 may be used to detect muscle regions. Alternatively, the CT image V0 may be displayed on the display 54, and the muscle region may be identified by manually specifying the muscle region in the displayed CT image V0.

[0068] Furthermore, the muscle density deriving unit 65 calculates the attenuation coefficient μm of the muscle using the above formula (2). Then, it acquires the muscle mass attenuation coefficient by referring to the table shown in Fig. 11. Then, it derives the muscle density ρm per unit volume using the above formula (4).

[0069] The statistical value derivation unit 66 obtains a statistical value for the subject H based on the bone density derived by the bone density derivation unit 63 and the muscle density derived by the muscle density derivation unit 65. The statistical value is used to calculate a fracture risk evaluation value for evaluating a fracture risk, as described below. Specifically, the statistical value derivation unit 66 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 formula (5). Q = W1 × Bd + W2 × Md (5)

[0070] W1 and W2 in formula (5) are weighting coefficients, which are determined by collecting a large number of bone density distribution index values ​​and muscle density distribution index values ​​and performing regression analysis.

[0071] The bone density distribution index value is a value that indicates how the bone density values ​​are spread. Examples of the bone density distribution index value include the value per unit area or unit volume of bone density, the average value, the median value, the maximum value, and the minimum value. The muscle density distribution index value is a value that indicates how the muscle density values ​​are spread. Examples of the muscle density distribution index value include the value per unit area or unit volume of muscle density, the average value, the median value, the maximum value, and the minimum value.

[0072] Furthermore, the statistical value derivation unit 66 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 density. For example, when obtaining the statistical value based on the bone density, muscle density, and age, the statistical value Q is calculated based on the bone density distribution index value Bd, the muscle mass distribution index value Md, and the age Y by the following formula (6). Q = W1 × Bd + W2 × Md + W3 × Y (6)

[0073] In formula (6), W1, W2, and W3 are weighting coefficients, and a large amount of data on bone density distribution index values, muscle density distribution index values, and the subject's ages corresponding to these index values ​​are collected, and the weighting coefficients W1, W2, and W3 are determined according to regression analysis based on the data. Note that even when calculating statistical values ​​by adding the subject's height, weight, fracture history, and the like in addition to age, it is preferable to multiply and add the weighting coefficients.

[0074] The evaluation value derivation unit 67 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 67 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.

[0075] 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 plain radiographic image G0). When equation (6) is used to calculate the statistical value Q as described above, the relationship between the "probability of fracture occurring within 10 years" and the "statistical value Q" is expressed as shown in FIG. 19 in which the larger the statistical value Q, the lower the fracture probability.

[0076] In the second embodiment, the fracture risk assessment value derived by the information derivation device 50A is used as the correct answer data of the training data. Fig. 20 is a diagram showing the training data derived in the second embodiment. As shown in Fig. 20, the training data 40B is composed of learning data 41 including a composite two-dimensional image C0 and correct answer data 42B which is a fracture risk assessment value.

[0077] By training a neural network using the training data 40B shown in FIG. 20, a trained neural network 23A can be constructed that, when a plain radiographic image G0 is input, outputs a fracture risk evaluation value as an estimated result related to bone density.

[0078] Next, a third embodiment of the present disclosure will be described. FIG. 21 is a diagram showing a functional configuration of an information derivation device according to a third embodiment. In FIG. 21, the same components as those in FIG. 7 are given the same reference numbers, and detailed descriptions are omitted. In the third embodiment of the present disclosure, instead of deriving bone density, information indicating a healing state of a bone part after treatment is derived as correct answer data 42. For this purpose, as shown in FIG. 21, an information derivation device 50B according to the third embodiment further includes a healing information derivation unit 68 in addition to the information derivation device 50 according to the first embodiment. In the third embodiment, it is assumed that surgery is performed to implant an artificial object such as an artificial bone into the bone part as a treatment of the bone part.

[0079] The healing information derivation unit 68 derives, as healing information, information indicating the state of the bone of the subject after the artificial object has been embedded in the bone of the subject H, based on the bone density around the artificial object, such as an artificial bone, embedded in the bone of the subject H. An artificial object, such as an artificial bone, is implanted in a living body by surgery to replace bone lost due to a comminuted fracture, a tumor, or the like.

[0080] Fig. 22 is a diagram showing an example of an artificial bone embedded in a bone of a subject. Fig. 22 shows an example of a bone of a subject H who has undergone artificial hip replacement surgery, and an artificial joint stem 81 is embedded in a femur 80 of the subject H.

[0081] Known methods for fixing the stem 81 include a direct fixation method (cementless fixation) and an indirect fixation method (cement fixation). In the direct fixation method, the stem 81 is inserted into the cavity inside the femur 80 without using cement. The cavity inside the femur 80 is shaped in advance so that the stem 81 fits into it. The surface of the stem 81 is roughened, and bone tissue grows so as to penetrate into the inside of the stem 81. That is, immediately after the stem 81 is embedded in the femur 80, a cavity exists between the stem 81 and the femur 80, but when the femur 80 recovers, the cavity shrinks and disappears as the bone tissue grows. Therefore, by obtaining the bone density around the stem 81, it is possible to grasp the degree of recovery of the femur 80 after surgery.

[0082] FIG. 23 is a graph showing an example of the relationship between the distance from the stem 81 inside the femur 80 and the bone density at each postoperative stage. The horizontal axis of the graph shown in FIG. 23 is the position along the line L in FIG. 22. In FIG. 23, the solid line corresponds to the initial stage immediately after the stem 81 is embedded in the femur 80, the dotted line corresponds to the stage during recovery, and the dashed line corresponds to the complete recovery stage. As shown in FIG. 23, in the initial postoperative stage, the femur 80 and the stem 81 are not in close contact with each other, and the bone density near the stem 81 is extremely low. As the bone tissue grows to penetrate toward the inside of the stem 81 with recovery, the bone density near the stem 81 increases. On the other hand, the bone density at a position far from the stem 81 is approximately constant at each postoperative stage. At the complete recovery stage, the bone density near the stem 81 and the bone density at the distant position are approximately equal.

[0083] In the following, a manner in which the healing information deriving unit 68 derives healing information will be described taking as an example a case in which an artificial hip replacement surgery shown in Fig. 22 is performed. The healing information deriving unit 68 derives healing information from a position L A Bone mineral density in A and the position X, which is relatively far from the stem 81 B Bone mineral density in BFor example, the healing information deriving unit 68 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 value derived as the healing information becomes smaller as the patient recovers and approaches 0. The healing information deriving unit 68 may also 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 with bone recovery and approaches 1. That is, the bone density B A and B B The value ΔB corresponding to the difference from the value ΔB can be said to be a value indicating 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 80 after surgery.

[0084] The healing information derivation unit 68 may derive healing information using the bone density per unit area in each pixel of the composite two-dimensional image C0 derived by the bone density derivation unit 63, or may derive healing information using the bone density per unit volume in each pixel of the CT image V0. Also, in the composite two-dimensional image C0, the pixel value of the stem 81 is significantly different from the pixel value in the bone region, so that it is possible to identify the region in which the stem 81 exists in the composite two-dimensional image C0. Therefore, the healing information derivation unit 68 can identify the distance from the stem 81 based on the composite two-dimensional image C0.

[0085] FIG. 24 is a cross-sectional view showing an example of a cross-sectional structure of a human bone. As shown in FIG. 24, a human bone is composed of cancellous bone 90 and cortical bone 91 covering the outside of the cancellous bone 90. The cortical bone 91 is harder and denser than the cancellous bone 90. The cancellous bone 90 is a collection of small bone pillars called trabeculae that extend into the marrow cavity. The trabeculae have a plate-like and rod-like structure and are connected to each other. Since the bone density of the cancellous bone 90 and the bone density of the cortical bone 91 are significantly different, it is possible to distinguish the cortical bone 91 from the cancellous bone 90 in the CT image V0. In particular, when the derived bone density is the bone density per unit volume, the bone density of the cancellous bone 90 and the bone density of the cortical bone 91 can be clearly distinguished from each other compared to the bone density per unit area.

[0086] When an artificial object is embedded in the cancellous bone 90, the healing information derivation unit 68 may specify the area of ​​the cancellous bone 90 based on the CT value of each pixel of the CT image V0, and derive healing information based on the bone density of the cancellous bone 90 around the artificial object. A Bone mineral density in A and position X in the cancellous bone 90, which is relatively far from the artificial object. B Bone mineral density in B A numerical value ΔB corresponding to the difference from the above may be derived as the cure information.

[0087] On the other hand, when an artificial object is embedded in the cortical bone 91, it is preferable that the healing information derivation unit 68 specifies the area of ​​the cortical bone 91 based on the CT value of each pixel of the CT image V0, and derives healing information based on the bone density of the cortical bone 91 around the artificial object. A Bone mineral density in A and position X in the cortical bone 91, which is relatively far from the artificial object. B Bone mineral density in B A numerical value ΔB corresponding to the difference from the above may be derived as the cure information.

[0088] Furthermore, when an artificial object embedded in the bone of the subject H extends to both the cancellous bone 90 and the cortical bone 91, the areas of the cancellous bone 90 and the cortical bone 91 may be specified based on the CT value of each pixel of the CT image V0, and healing information may be derived based on the bone densities of both the cancellous bone 90 and the cortical bone 91 around the artificial object. A1 Bone mineral density in A1 and position L in the cancellous bone 90, which is relatively far from the artificial object. B1 Bone mineral density in B1 A numerical value ΔB1 according to the difference from the artificial object is derived as healing information, and a position L A2 Bone mineral density in A2 and a position L in the cortical bone 91 that is relatively far from the artificial object. B2 Bone mineral density in B2 A numerical value ΔB2 according to the difference between the artificial object embedded in the bone portion of the subject H and the cancellous bone 90 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 90 and the cortical bone 91, the healing information may be derived based on the bone density of one of the cancellous bone 90 and the cortical bone 91 around the artificial object. In other words, one of the numerical value ΔB1 and the numerical value ΔB2 may be derived as the healing information.

[0089] In the third embodiment, the cure information derived by the information derivation device 50B is used as the correct answer data of the teacher data. Fig. 25 is a diagram showing the teacher data derived in the third embodiment. As shown in Fig. 25, the teacher data 40C is composed of learning data 41 including a composite two-dimensional image C0 and correct answer data 42C which is a numerical value of the cure information.

[0090] By training a neural network using the teacher data 40C shown in FIG. 25, 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.

[0091] In each of the above embodiments, a bone density image having pixel values ​​representing bone density per unit area or per unit volume derived by the bone density derivation unit 63 may be used as the correct answer data 42 of the teacher 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.

[0092] FIG. 26 is a diagram showing another example of the display screen of the estimation result. As shown in FIG. 26, the display screen 70A has an image display area 71 similar to the display screen 70 shown in FIG. 14. The image display area 71 displays a bone density image Gd, which is an estimation result of the bone density in the simple radiation image G0 of the subject H. In the bone density image Gd, a pattern is added to the bone area according to the bone density. In FIG. 26, for the sake of simplicity, a pattern representing the bone salt amount is added only to the femur. A reference 73 indicating the magnitude of the bone salt amount for the added pattern is displayed below the image display area 71. The operator can easily recognize the bone density of the patient by reading the bone density image Gd while referring to the reference 73. Instead of a pattern, a different color may be added to the bone density image Gd according to the bone density.

[0093] In addition, in each of the above embodiments, information related to bone density of the femur near the hip joint is estimated, but the target bone is not limited to the femur. The technology disclosed herein can also be applied to estimating information related to bone density of any bone part, such as the femur and tibia near the knee joint, vertebrae such as the lumbar vertebrae, the calcaneus, and the metacarpals.

[0094] In addition, in each of the above-mentioned embodiments, the estimation result related to bone density is derived from the simple radiation image G0, but the present invention is not limited to this. For example, the technology of the present disclosure can be applied to the case where the estimation result related to bone density is derived from the DXA scan image obtained by photographing the subject with the DXA imaging device described in Japanese Patent Application Laid-Open No. 9-108206 and Japanese Patent Application Laid-Open No. 2006-271437. The DXA scan image refers to a radiation image captured by a radiation detector, in which a thin collimated high-energy radiation beam and a low-energy radiation beam are irradiated to the subject while switching and scanning. The thin collimated radiation beam is, for example, a radiation beam formed into a pencil beam, a narrow fan beam, a wide fan beam, or the like, using a collimator between the radiation source and the subject. The low-energy radiation refers to radiation with energy relatively lower than that of the high-energy radiation.

[0095] In this case, an image simulating the DXA scan image may be generated from the composite two-dimensional image C0 according to various conditions such as the pixel size of the detector that captures the DXA scan image, the scanning direction and scanning speed during imaging, the mutual distances between the X-ray source, subject, and detector, and the radiation energy distribution (determined by the tube voltage, target, and filter), and the generated image simulating the DXA scan image may be used as training data 41 to construct the trained neural network 23A.

[0096] The image simulating the DXA scan image may be generated, for example, by performing a process of reducing the resolution of the composite two-dimensional image C0 in accordance with the pixel size, scanning direction, scanning speed, etc. of the detector used to capture the DXA scan image. The image simulating the DXA scan image is an example of a low-resolution composite two-dimensional image.

[0097] Specifically, an image simulating a DXA scan image is generated as follows. Let us assume that M×M pixels of the composite two-dimensional image C0 correspond to the actual size of the subject H, Lmm×Lmm, and N×N pixels of the learning image of the DXA scan image correspond to the actual size of the subject H, where L, M, and N are natural numbers. In this case, the average value of the pixel values ​​of the (M / N)×(M / N) pixels of the composite two-dimensional image C0 is set to all (M / N)×(M / N) pixels of the composite two-dimensional image C0 so that (M / N)×(M / N) pixels of the composite two-dimensional image C0, i.e., adjacent pixels, correspond to one pixel of the learning image of the DXA scan image, thereby reducing the resolution of the composite two-dimensional image C0. Then, by performing such a resolution reduction process on all areas of the composite two-dimensional image C0 that correspond to the DXA scan image, an image simulating a DXA scan image is generated. If M / N is not a natural number, the positions of corresponding pixels in the composite 2D image C0 and the learning image of the DXA scan image can be adjusted appropriately using natural numbers before or after M / N to generate an image that simulates the DXA scan image from the composite 2D image C0.

[0098] Furthermore, as a resolution reduction process for simulating blurring due to scanning, an image simulating a DXA scanned image may be generated by performing a moving average process in one direction corresponding to the scanning direction.

[0099] Also, a moving average process may be performed on the composite two-dimensional image C0 to generate an image simulating a DXA scan image. The moving average process may be performed by appropriately determining the size of the filter and the intensity distribution of the filter used to calculate the moving average based on the scanning direction when the DXA scan image is captured, the scanning speed, the pixel size of the detector, and the distances between the X-ray source, the subject, and the detector. For example, the faster the scanning speed, the lower the resolution, so the larger the filter size should be set. In this case, when L=10 is set, M=200 and N=5.

[0100] In each of the above embodiments, bone density, fracture risk, and healing information are used as correct answer data included in the teacher data for learning the neural network. Therefore, the information related to bone density that the estimation unit 23 estimates from the simple radiographic image G0 is the bone density, fracture risk, and healing information in the simple radiographic image G0, but is not limited thereto. 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 simple radiographic image G0 as information related to bone density. In addition, the estimation unit 23 may use the detection results of the presence or absence of a fracture, the presence or absence of a tumor, and the presence or absence of an implant, or may use the judgment result of osteoporosis, as the information related to bone density to be estimated. In addition, bone diseases related to bone density, such as multiple myeloma, rheumatism, arthropathy, and cartilage sclerosis, may be estimated as information related to bone density. In this case, the trained neural network 23A may be constructed using teacher data including these pieces of information related to bone density as correct answer data.

[0101] In each of the above embodiments, the trained neural network 23A is constructed by training the neural network in the estimation device 10, but the present invention is not limited to this. The 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.

[0102] Furthermore, in each of the above embodiments, the bone density related information is estimated using a radiological image acquired in a system that uses a radiation detector 5 to image the subject H. However, the technology of the present disclosure can also be applied to a case in which a radiological image is acquired using a storage phosphor sheet instead of a radiation detector.

[0103] Moreover, the radiation in the above embodiment is not particularly limited, and in addition to X-rays, α-rays, γ-rays, etc. can be used.

[0104] In the above embodiment, the following various processors can be used as the hardware structure of the processing units that execute 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, synthesis unit 62, and bone density derivation unit 63 of the information derivation device 50. The above various processors include, as described above, 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 a dedicated electric circuit, such as an ASIC (Application Specific Integrated Circuit), which is a processor having a circuit configuration designed specifically to execute specific processes.

[0105] 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 (e.g., 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.

[0106] As an example of configuring multiple processing units with one processor, first, there is a form in which one processor is configured with a combination of one or more CPUs and software, as typified by computers such as client and server, and this processor functions as multiple processing units. Second, there is a form in which a processor is used that realizes the functions of the entire system including multiple processing units with one IC (Integrated Circuit) chip, as typified by System On Chip (SoC), etc. In this way, the various processing units are configured using one or more of the above various processors as a hardware structure.

[0107] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. [Explanation of symbols]

[0108] 1. Imaging device 3 Radiation source 5. Radiation detectors 7 CT device 9. Image Storage System 10 Estimation device 11, 51 CPU 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 18, 58 Bus 21 Image acquisition unit 22 Information Acquisition Department 23 Estimation part 23A Trained Neural Networks 24 Learning Department 25 Display control section 30 Neural Networks 31 Input Layer 32 Middle Class 33 Output layer 35 Convolutional Layer 36 Pooling Layer 37 Fully connected layer 40, 40A, 40B, 40C Teacher data 41 Training Data 42, 42A, 42B, 42C Correct data 47 Output Data 48 Parameters 50, 50A, 50B Information derivation device 52 Information derivation program 61 Image acquisition unit 62 Synthesis section 63 Bone density derivation section 64 plane 65 Muscle density extraction section 66 Statistical Value Derivation Section 67 Evaluation value derivation part 68 Cure Information Derivation Unit 70, 70A display screen 71 Image display area 72 Bone density display area 73 References 80 Femur 81 Stem 90 Cancellous bone 91 Cortical bone C0 Composite 2D image G0 Plain radiographic image Gd bone density imaging L distance Q Statistic V0 CT image

Claims

1. At least one processor; The processor, The neural network functions as a trained neural network that derives an estimation result related to bone density of a bone portion from a simple radiographic image obtained by simply photographing a subject including a bone portion or a DXA scanned image obtained by photographing the subject using a DXA method; The trained neural network is trained using a synthetic two-dimensional image representing the subject derived by synthesizing three-dimensional CT images of the subject and information related to the bone density of the subject as training data.

2. The estimation device according to claim 1 , wherein the synthetic two-dimensional image is derived by deriving a radiation attenuation coefficient for a composition at each position in three-dimensional space, and projecting the CT image in a predetermined direction based on the attenuation coefficient.

3. 3. The estimation device according to claim 1, wherein the information related to the bone density is derived by identifying a bone region in the CT image, deriving an attenuation coefficient of radiation in the bone region, and deriving the bone density at each position of the bone region based on the attenuation coefficient of the radiation and the mass attenuation coefficient in the bone region.

4. The estimation device according to claim 3 , wherein the information relating to the bone density is derived by projecting the bone density at each position in the bone region in a predetermined direction.

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

6. the processor functions as a trained neural network to derive an inference related to bone mineral density of the bone portion from the DXA scan image; 6. The estimation device according to claim 1, wherein the trained neural network is trained using a low-resolution composite two-dimensional image obtained by performing a process to reduce the resolution of the composite two-dimensional image and information related to the bone density of the subject as training data.

7. 7. The estimation device according to claim 6, wherein the low-resolution composite two-dimensional image is an image in which the pixel value of the adjacent pixels is an average value of the pixel values ​​of adjacent pixels of the composite two-dimensional image, and a size of the adjacent pixels corresponds to a size of one pixel of the DXA scan image.

8. 7. The estimation device according to claim 6, wherein the low-resolution composite two-dimensional image is an image obtained by performing a moving average process on one direction of the composite two-dimensional image, the one direction corresponding to a scanning direction of the DXA scan image.

9. 7. The estimation device according to claim 6, wherein the low-resolution composite two-dimensional image is an image generated by generating a first low-resolution image in which the pixel value of adjacent pixels in the composite two-dimensional image is an average value of the pixel values ​​of the adjacent pixels, and performing a moving average process in one direction on the first low-resolution image, wherein a size of the adjacent pixels corresponds to a pixel size of one pixel in the DXA scanned image, and the one direction corresponds to a scanning direction of the DXA scanned image.

10. 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 or a DXA scanned image obtained by photographing the subject using a DXA method, using a trained neural network that derives an estimation result related to bone density of the bone portion from the simple radiographic image or the DXA scanned image, the method comprising: An estimation method, in which the trained neural network is trained using a synthetic two-dimensional image representing the subject derived by synthesizing three-dimensional CT images of the subject and information related to the bone density of the subject as training data.

11. An estimation program for causing a computer to execute a procedure for deriving an estimation result related to bone density from a plain radiographic image or a DXA scanned image obtained by simply photographing a subject including a bone portion or a DXA scanned image obtained by photographing the subject using a DXA method, using a trained neural network for deriving an estimation result related to bone density from the plain radiographic image or the DXA scanned image, The trained neural network is trained using a synthetic two-dimensional image representing the subject derived by synthesizing three-dimensional CT images of the subject and information related to the bone density of the subject as training data.

Images