Abstract: A radiation image processing apparatus according to an embodiment of the present invention acquires at least two radiation images in which a plurality of radiation energies different from each other are used, respectively, for the same subject, calculates a fat percentage occupied in a soft tissue of the subject by subtraction processing with respect to the two radiation images, and applies the fat percentage to the subtraction processing with respect to another image that is a radiation image in which the subject is imaged at a different timing.

Abstract: A processor derives, based on at least one radiation image based on radiation that is transmitted through a subject including a plurality of compositions, a thickness of at least one composition of the plurality of compositions for each pixel of the radiation image, and derives a composition image for the at least one composition by using an attenuation coefficient based only on the thickness of the at least one composition.

Abstract: A processor acquires two radiation images based on radiation that is transmitted through a subject including a plurality of compositions and has different energy distributions from each other, derives body thicknesses of the subject as a first body thickness and a second body thickness, respectively, for each pixel for each of the two radiation images by using an attenuation coefficient according to an order in which the radiation is transmitted through the plurality of compositions, and derives a composition ratio of the subject for each pixel of the radiation image based on the first body thickness and the second body thickness.

Abstract: A radiation image processing apparatus generates a first emphasis image by performing first emphasis processing on two radiation images, which are different from each other, in which a specific subject is imaged, generates a second emphasis image by performing second emphasis processing using at least any radiation image of the two radiation images, and generates correlation information between the first emphasis image and the second emphasis image. The radiation image processing apparatus displays the first emphasis image, a level value corresponding to a value of a first parameter, and an image quality indicator in which a difference between the first emphasis image and the second emphasis image is quantified, and receives a change of the level value.

Abstract: In a case of deriving a subtraction image in which a specific tissue in a subject is extracted, the subtraction image being derived by performing weighting subtraction on a plurality of radiation images acquired by imaging the subject with radiation having different energy distributions and being subjected to predetermined image processing, a reaching dose which is a radiation dose that directly reaches a radiation detector that acquires the radiation image is acquired, and the subtraction image is derived by performing the image processing based on the reaching dose.

Abstract: A processor displays a subtraction image in which a specific tissue in a subject is extracted, the subtraction image being derived by performing weighting subtraction on a plurality of radiation images acquired by imaging the subject with radiation having different energy distributions and being subjected to predetermined image processing, receives an instruction to change a subtraction level corresponding to a weight coefficient used in a case of performing the weighting subtraction, determines whether or not a change amount of the subtraction level exceeds a predetermined threshold value, and issues a warning in a case in which the determination is affirmative.

Abstract: An information processing apparatus includes a soft part image generation unit that generates a soft part image representing a soft part region with a soft tissue of a subject from a first radiographic image and a second radiographic image acquired by radiation having different energy distributions transmitted through the subject, and a muscle mass derivation unit that derives a muscle mass based on a pixel value for each pixel of the soft part region of the soft part image.

Abstract: The radiation image analysis device acquires an X-ray image obtained by performing X-ray radiography on a subject including a bone part, acquires a rotation angle from a reference position of the bone part on the basis of the X-ray image, and acquires bone quantity information of the bone part by correcting pre-correction bone quantity information of the bone part obtained by converting a pixel value for each pixel of the X-ray image on the basis of the rotation angle.

Abstract: A processor derives a bone part image of a subject including a bone part based on a first radiation image and a second radiation image acquired by imaging the subject with radiation having different energy distributions, derives a fat percentage distribution or a muscle percentage distribution of the subject based on the first radiation image and the second radiation image, and derives a bone density in a bone region of the subject based on the bone part image, and the fat percentage distribution or the muscle percentage distribution.

Abstract: A processor functions as a trained neural network that derives an estimation result relating to a three-dimensional bone density of a bone part from a simple radiation image acquired by simply imaging a subject including the bone part, or a DXA scanning image acquired by imaging the subject by a DXA method. The trained neural network learns using, as teacher data, (i) two radiation images or the like acquired by imaging the subject including the bone part with radiation having different energy distributions, and a two-dimensional bone density of the bone part included in the two radiation images or the like, or (ii) the radiation image or the like of the subject or a bone part image representing the bone part of the subject, the two-dimensional bone density of the bone part included in the radiation image or the like, or the bone part image, and the three-dimensional bone density of the bone part of the subject.

Abstract: A processor acquires first-direction and second-direction radiographic images captured by emitting radiation in different directions. The processor derives a bone mineral content for each pixel in the bone portion included in the first-direction and second-direction radiographic images. The processor divides the bone portion included in the first-direction and second-direction radiographic images into a plurality of small regions and derives first and second evaluation results for each small region of the bone portion on the basis of the derived bone mineral content.

Abstract: At least one processor is provided, in which the processor functions as a trained neural network that derives an estimation result relating to a composition of a soft tissue of a subject from a simple radiation image acquired by simply imaging the subject, or a DXA scanning image acquired by imaging the subject by a DXA method. The trained neural network learns using, as teacher data, two radiation images acquired by imaging the subject with radiation having different energy distributions, the radiation image of the subject and a soft part image representing the soft tissue of the subject, or a composite two-dimensional image representing the subject derived by combining a three-dimensional CT image of the subject, and information relating to the composition of the soft tissue of the subject.

Abstract: An estimation device includes at least one processor, in which the processor functions as a learned neural network that derives a result of estimation of at least one emphasis image in which a specific composition of a subject including a plurality of compositions is emphasized from a simple two-dimensional image acquired by simply imaging the subject. The learned neural network is learned by using, as teacher data, a composite two-dimensional image representing the subject, which is derived by combining a three-dimensional CT image of the subject, and an emphasis image for learning in which the specific composition of the subject is emphasized, which is derived from the CT image.

Abstract: An estimation device includes at least one processor, in which the processor functions as a learned neural network that derives a result of estimation of at least one emphasis image in which a specific composition of a subject including a plurality of compositions is emphasized from a simple two-dimensional image acquired by simply imaging the subject. The learned neural network is learned by using, as teacher data, two radiation images acquired by imaging the subject with radiation having different energy distributions and an emphasis image for learning in which the specific composition of the subject is emphasized, which is derived from the two radiation images.

Abstract: An estimation device includes at least one processor, in which the processor functions as a learned neural network that derives a result of estimation relating to a bone density of a bone part from a simple radiation image acquired by simply imaging 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 with radiation having different energy distributions, (ii) the radiation image of the subject and a bone part image representing the bone part of the subject, or (iii) the radiation image of the subject and a bone density image representing the bone density of the bone part of the subject, and information relating to the bone density of the bone part of the subject.

Abstract: An estimation device includes at least one processor, in which the processor functions as a learned neural network that derives a result of estimation relating to a bone density of a bone part from a simple radiation image acquired by simply imaging a subject including the bone part or a DXA scanning 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 representing the subject, which is derived by combining a three-dimensional CT image of the subject, and information relating to the bone density of the subject.

Abstract: An information processing apparatus includes a bone part image generation unit that generates a bone part image in which a bone part of a subject is highlighted, from a first radiographic image and a second radiographic image acquired by radiation having different energy distributions transmitted through the subject, a bone mineral content derivation unit that derives a bone mineral content for each pixel of the bone part image, and a postoperative information derivation unit that, based on a bone mineral content around an artificial object implanted in the bone part of the subject, derives information indicating a state of the bone part of the subject after the artificial object is implanted in the bone part of the subject, as postoperative information.

Abstract: A processor acquires first-direction and second-direction radiographic images captured by emitting radiation in different directions. The processor derives a bone mineral content for each pixel in the bone portion included in the first-direction and second-direction radiographic images. The processor divides the bone portion included in the first-direction and second-direction radiographic images into a plurality of small regions and derives first and second evaluation results for each small region of the bone portion on the basis of the derived bone mineral content.

Abstract: An image processing apparatus includes a first acquisition unit, a derivation unit, a second acquisition unit, and a trabecula image generation unit. The first acquisition unit acquires a first radiographic image and a second radiographic image by simple imaging of a subject including a bone tissue. The derivation unit derives a bone mass in a bone part region of the subject based on the first radiographic image and the second radiographic image. The second acquisition unit acquires a medical image that represents a state of a trabecula and is different from the first radiographic image and the second radiographic image. The trabecula image generation unit applies the medical image to the bone part region of the first radiographic image based on the bone mass derived by the derivation unit to generate a trabecula image representing a trabecula of the bone tissue.

Abstract: An information processing apparatus includes a soft part image generation unit that generates a soft part image representing a soft part region with a soft tissue of a subject from a first radiographic image and a second radiographic image acquired by radiation having different energy distributions transmitted through the subject, and a muscle mass derivation unit that derives a muscle mass based on a pixel value for each pixel of the soft part region of the soft part image.