Journal article

Novel mammogram-based measures improve breast cancer risk prediction beyond an established mammographic density measure

Tuong L Nguyen, Daniel F Schmidt, Enes Makalic, Gertraud Maskarinec, Shuai Li, Gillian S Dite, Ye K Aung, Christopher F Evans, Ho N Trinh, Laura Baglietto, Jennifer Stone, Yun-Mi Song, Joohon Sung, Robert J MacInnis, Pierre-Antoine Dugue, James G Dowty, Mark A Jenkins, Roger L Milne, Melissa C Southey, Graham G Giles Show all



Mammograms contain information that predicts breast cancer risk. We developed two novel mammogram-based breast cancer risk measures based on image brightness (Cirrocumulus) and texture (Cirrus). Their risk prediction when fitted together, and with an established measure of conventional mammographic density (Cumulus), is not known. We used three studies consisting of: 168 interval cases and 498 matched controls; 422 screen-detected cases and 1197 matched controls; and 354 younger-diagnosis cases and 944 controls frequency-matched for age at mammogram. We conducted conditional and unconditional logistic regression analyses of individually- and frequency-matched studies, respectively. We estima..

View full abstract


Awarded by Cure Cancer Australia

Awarded by National Health and Medical Research Council

Funding Acknowledgements

Cure Cancer Australia, Grant/Award Number: 1159399; National Health and Medical Research Council, Grant/Award Numbers: 209057, 251533, 504711; Victorian Comprehensive Cancer Centre; Picchi Foundation; University of Melbourne; Victoria Breast Cancer Research Consortium; Breast Cancer Network Australia; National Breast Cancer Foundation; Cancer Australia; Cancer Council NSW; Cancer Council Victoria; Victorian Health Promotion Foundation