This diagnostic image processing apparatus receives an input of an X-ray image of a hand or a foot, detects, in the X-ray image, the imaging range of the left hand, the right hand, the left foot, or the right foot, and extracts, at least for each joint located in the detected imaging range and used for assessment by using an assessment method selected from either van der Heijde method or Genant method, portions of relatively high luminance from the opposing ends of a pair of bones located across each of the joints. Then, the diagnostic image processing apparatus generates and outputs information about a distance and an area between the extracted high luminance parts as diagnosis information for each joint used for the assessment carried out by the selected assessment method.