Novel mammogram‐based measures improve breast cancer risk prediction beyond an established mammographic density measure. Issue 9 (4th December 2020)

• Record Type: Journal Article
• Authors: Nguyen, Tuong L.; Schmidt, Daniel F.; Makalic, Enes; Maskarinec, Gertraud; Li, Shuai; Dite, Gillian S.; Aung, Ye K.; Evans, Christopher F.; Trinh, Ho N.; Baglietto, Laura; Stone, Jennifer; Song, Yun‐Mi; Sung, Joohon; MacInnis, Robert J.; Dugué, Pierre‐Antoine; Dowty, James G.; Jenkins, Mark A.; Milne, Roger L.; Southey, Melissa C.; Giles, Graham G.; Hopper, John L.
• Is Part Of: International journal of cancer. Volume 148:Issue 9(2021)
• Page Start: 2193
• Page End: 2202
• Publication Date: 2020-12-04
• Subjects: breast cancer -- Cirrocumulus -- Cirrus -- interval breast cancer -- mammographic density -- screen‐detected breast cancer; Cancer -- Periodicals; Cancer -- Prevention -- Periodicals; 616.994
• DOI: 10.1002/ijc.33396
• Languages: English
• ISSNs: 0020-7136

Abstract

Abstract: 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 estimated measure‐specific risk gradients as the change in odds per standard deviation of controls after adjusting for age and body mass index (OPERA) and calculated the area under the receiver operating characteristic curve (AUC). For interval, screen‐detected and younger‐diagnosis cancer risks, the best fitting models (OPERAs [95% confidence intervals]) involved: Cumulus (1.81 [1.41‐2.31]) and Cirrus (1.72 [1.38‐2.14]); Cirrus (1.49 [1.32‐1.67]) and Cirrocumulus (1.16 [1.03 to 1.31]); and Cirrus (1.70 [1.48 to 1.94]) and Cirrocumulus (1.46 [1.27‐1.68]), respectively. The AUCs were: 0.73 [0.68‐0.77], 0.63 [0.60‐0.66], and 0.72 [0.69‐0.75], respectively. Combined, our new mammogram‐based measures have twice the risk gradient for screen‐detected and younger‐diagnosis breast cancer ( P ≤ 10 −12 ), have at least the same discriminatory power as the current polygenic risk score, and are more correlated with causal factors than conventional mammographic density. Discovering more information about breast cancer risk from mammograms could help enable risk‐based personalised breast screening. Abstract : What's new? Mammographic density, or the area of the mammogram which appears white or bright, has well‐established associations with breast cancer risk. The authors call this Cumulus due to the computer‐assisted technique for measuring that density. Here, the authors introduce two novel measurement techniques, Cirrus and Cirrocumulus, for extracting risk information from mammograms. Cirrocumulus is based on image brightness and Cirrus is based on texture. When combined, these measures substantially improve risk prediction beyond that of Cumulus . In addition, the new risk measures outperformed the recently published polygenic risk score. By obtaining more information from mammograms, these tools could improve personalized risk recommendations for screening.