An image processing apparatus comprising: first image obtaining means for obtaining a first image of an object in a first shape state; region of interest setting means for setting a region of interest of the object on the first image; deformation information obtaining means for obtaining deformation information indicating deformation of the object from the first shape state to a second shape state; region calculating means for calculating a region in the second shape state corresponding to the region of interest in the first shape state based on the deformation information; and imaging region setting means for setting an imaging region of the object in the second shape state based on the region calculated by the region calculating means.