Autodensity: A testing platform for automated breast density measurement techniques
Mammographic breast density describes the denser tissue in breasts that appears whiter on mammograms. High levels of apparent breast density are associated with an increased risk of breast cancer[1,2] and poorer performance of breast cancer screening programs[3,4]. The 2009 BreastScreen Australia Evaluation recommended the development of a national policy based on a review of the available evidence in relation to identifying and managing women according to their breast density, following the implementation of digital mammography in BreastScreen Australia.
This exciting partnership between the University of Melbourne, the CSIRO Australian e-Health Research Centre and BreastScreen Victoria aims to epidemiologically test automated methods for reading breast density in a standardised way, with a view to identifying the best method for predicting breast cancer risk and/or screening program sensitivity.
We invite developers of automated breast density reading methods that have demonstrated good validation so far against either existing breast density measures, breast cancer risk or breast cancer screening performance to work with us to further validate their automated methods.
Our study has access to a case-control set of digitally acquired BreastScreen Victoria mammograms for 400 cases (breast cancers detected by screening or between screens) and 2,000 controls (true negative and false positive screens), along with routinely collected information such as age, hormone replacement therapy use, family history of breast cancer and for cases, tumour characteristics.
We also have access to a large case-control set of scanned BreastScreen film mammograms (approx. 3,000 cases and 7,000 controls) from screens conducted in the mid-1990s, also with associated epidemiological data. These data have already been studied extensively [6-8] using the Cumulus greyscale threshold technique for measuring breast density . Although many radiology services are gradually shifting from film to digital mammography, breast density readings from film mammograms will be of interest for research purposes for many years to come and automated methods would substantially increase the capacity of research in this area.
Our study is governed by ethics approvals from the University of Melbourne Human Research Ethics Committee and research approval from the BreastScreen Victoria Research and Evaluation Committee. We are currently funded by a University of Melbourne Collaboration Grant and a Victorian Breast Cancer Research Consortium Research Translation Grant.
All enquiries are welcome. Please contact principal investigator Dr Carolyn Nickson, email firstname.lastname@example.org, telephone +61 3 8344 0765.
The research team
University of Melbourne
- Dr Carolyn Nickson, Research Fellow, Centre for Women’s Health, Gender and Society, Melbourne School of Population and Global Health
- Professor Dallas English, Director, Centre for MEGA Epidemiology, Melbourne School of Population and Global Health
- Professor Rao Kotagiri, Department of Computer Science and Software Engineering
- Professor Anne Kavanagh, Director, Centre for Women’s Health, Gender and Society, Melbourne School of Population and Global Health
- Dr Md Rafiul Hassan, Department of Computer Science and Software Engineering
- Ms Rachel Li, Centre for Women’s Health, Gender and Society and Department of Computer Science and Software Engineering
- A/Professor Jenny Cawson, St Vincent's BreastScreen, BreastScreen Victoria
CSIRO ICT Australian eHealth Research Centre
- Dr Olivier Salvado, Team Leader, Biomedical Imaging Unit, Australian eHealth Research Centre, Brisbane Hospital
- Dr Jason Dowling, Biomedical Imaging Unit, Australian eHealth Research Centre, Brisbane Hospital
- Dr Yulia Arzhaeva , CSIRO Mathematics, Informatics and Statistics, Sydney
1. Boyd, N.F., J.W. Byng, R.A. Jong, E.K. Fishell, L.E. Little, A.B. Miller, G.A. Lockwood, D.L. Tritchler, and M.J. Yaffe, Quantitative classification of mammographic densities and breast cancer risk: results from the Canadian National Breast Screening Study. J Natl Cancer Inst, 1995. 87(9): p. 670-5.
2. Brisson, J., C. Diorio, and B. Masse, Wolfe's parenchymal pattern and percentage of the breast with mammographic densities: redundant or complementary classifications? Cancer Epidemiol Biomarkers Prev, 2003. 12(8): p. 728-32.
3. Carney, P.A., D.L. Miglioretti, B.C. Yankaskas, K. Kerlikowske, R. Rosenberg, C.M. Rutter, B.M. Geller, L.A. Abraham, S.H. Taplin, M. Dignan, G. Cutter, and R. Ballard-Barbash, Individual and combined effects of age, breast density, and hormone replacement therapy use on the accuracy of screening mammography. Ann Intern Med, 2003. 138(3): p. 168-75.
4. Sala, E., R. Warren, J. McCann, S. Duffy, R. Luben, and N. Day, High-risk mammographic parenchymal patterns, hormone replacement therapy and other risk factors: a case-control study. Int J Epidemiol, 2000. 29(4): p. 629-36.
5. Australian Department of Health and Ageing. Program. Screening Monograph No. 1/2009 - BreastScreen Australia Evaluation: Evaluation Final Report, June 2009. Available from: http://www.health.gov.au/internet/screening/publishing.nsf/Content/br-evaluation-report-cnt
6. Kavanagh, A.M., G.B. Byrnes, C. Nickson, J.N. Cawson, G.G. Giles, J.L. Hopper, D.M. Gertig, and D.R. English, Using mammographic density to improve breast cancer screening outcomes. Cancer Epidemiol Biomarkers Prev, 2008. 17(10): p. 2818-24.
7. Kavanagh, A.M., J. Cawson, G.B. Byrnes, G.G. Giles, G. Marr, B. Tong, D.M. Gertig, and J.L. Hopper, Hormone replacement therapy, percent mammographic density, and sensitivity of mammography. Cancer Epidemiol Biomarkers Prev, 2005. 14(5): p. 1060-4.
8. Nickson, C. and A.M. Kavanagh, Tumour size at detection according to different measures of mammographic breast density. J Med Screen, 2009. 16(3): p. 140-6.
9. Byng, J.W., N.F. Boyd, E. Fishell, R.A. Jong, and M.J. Yaffe, The quantitative analysis of mammographic densities. Phys Med Biol, 1994. 39(10): p. 1629-38.