Breast Cancer Surveillance Consortium: Working together to advance breast cancer research
Home   |   Data   |   Statistics   |   Tools   |   Collaborations   |   Work with Us   |   Publications   |   About   |   Links

Dense Breast Tissue Volume and Image Texture Features Assocation with Breast Cancer Risk

Grant number: U01CA063740-15S1
PI Name: Kerlikowske K
Title: Dense Breast Tissue Volume and Image Texture Features Assocation with Breast Cancer Risk

Mammography is an ideal time to assess risk of breast cancer because breast density, one of the strongest risk factors for breast cancer, can be assessed from the patient's mammogram. Clinical risk factors are already assessed at the time of mammography. The combination of a qualitative measure of breast density and risk factors estimates a patient's risk of breast cancer more accurately than does either alone, but prediction is still modest. We have successfully added an automated quantitative measurement of breast density (dense breast volume) into routine mammography visits at four facilities in the San Francisco Mammography Registry (SFMR) with a supplement to the SFMR in 2007. We have collected about 79,000 raw digital images and propose to develop new methods to measure 22 texture features on these 79,000 breast images and test their association with clinical risk factors, dense breast volume, and breast cancer. With support from this proposal, we specifically will:

Aim 1: Examine the correlation of image texture features with clinical risk factors and dense volume measured on digital screening examinations;

Aim 2: Determine the association of texture features of breast cancer of 433 breast cancers and 1,300 controls, adjusting for dense volume and clinical breast cancer risk factors compared with risk factors only; and

Aim 3: Determine the sensitivity of texture features combined with dense volume and other risk factors to classify women into those with and without breast cancer compared with risk factors only.

This project builds on one of the parent grant's primary goals to expand the San Francisco Mammography Registry's rich resource by including new variables (image texture features) in our database and to use these variables to conduct high quality, clinically significant research related to breast health and breast cancer. The supplement also fulfills the goals of the Recovery Act since the raw digital images and the new measures assessed on images will expand our resource available to potential collaborators.