Motor organ disease prediction device, motor organ disease prediction method, motor organ disease prediction program, learning device, learning method, learning program, and learned neural network

Abstract

A motor organ disease prediction device includes at least one processor, in which the processor derives a bone mineral density of a target bone among bones included in a subject including a bone part and a soft part, a muscle mass around the target bone, shape information representing a shape of the target bone, and shape information representing a shape of a bone adjacent to the target bone from a first radiation image and a second radiation image acquired by imaging the subject by radiation having different energy distributions. The processor derives a probability of occurrence of a motor organ disease relating to the target bone from the bone mineral density of the target bone, the muscle mass around the target bone, the shape information of the target bone, and the shape information of the bone adjacent to the target bone.