A medical image processing apparatus includes a selection unit which selects a combination of images acquired in substantially equal time phases in a cycle from a first image group including a plurality of first images acquired at different time points in a first period by imaging an organ whose shape cyclically varies and a second image group including a plurality of second images acquired at different time points in a second period different from the first period by imaging the organ based on a characteristics value indicative of characteristics of the shape of the organ measured from the first and second image groups, and a generation unit which generates combination information indicative of the combination selected by the selection unit.