A medical image processing device includes a motion amount calculating unit configured to compare a first image obtained by capturing a subject image taken by an endoscope with a second image obtained by capturing the subject image at a chronologically different timing from the first image and calculate a motion amount for the second image every two or more areas in the first image; and an area specifying unit configured to specify a mask area other than the subject image included in the first image from an inside of a mask candidate area in which the motion amount is equal to or less than a specific first threshold value in the first image.