Breast density is considered a structural property of  a  mammogram  that  can  change  in  various  ways  explaining
different effects of medicinal treatments. The aim of the present work  is  to  provide  a  framework  for  obtaining  more  accurate and sensitive measurements of breast density changes related to  specific  effects  like  Hormonal  Replacement  Therapy  (HRT) and aging. Given effect-grouped patient data, we demonstrated how  anisotropic  diffusion  tensor  and  its  coherence  features computed in an anatomically oriented breast coordinate system
followed by statistical learning scheme provides non subjective and   reproducible   measure   compare   it   to   the   traditional BIRADS and computer aided percent density measure. We also demonstrate   how   orientation   of   breast   tissue   changes   in temporal study. This framework facilitates radiologist to assess breast tissue change and guide them to evaluate individual risk of having breast cancer.