According to one embodiment, an image interpretation report creating apparatus that creates an image interpretation report including a finding and is associated with a key image, includes a key image selecting unit, a position detecting unit, a first local structure information generating unit, and a display. A key image selecting unit selects a sub-image as the key image from among a plurality of sub-images comprising a medical image. A position detecting unit detects a position of a characteristic local structure in a human body from the medical image. A first local structure information generating unit identifies a local structure in the key image or in a vicinity of the key image and generates information on the identified local structure as first local structure information. A display displays the first local structure information as a candidate to be entered in an entry field for the finding.
