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.