Percent mammographic density prediction: development of a model in the nurses’ health studies

Abstract

Purpose To develop a model to predict percent mammographic density (MD) using questionnaire data and mammograms from controls in the Nurses’ Health Studies’ nested breast cancer case-control studies. Further, we assessed the association between both measured and predicted percent MD and breast cancer risk. Methods Using data from 2955 controls, we assessed several variables as potential predictors. We randomly divided our dataset into a training dataset (two-thirds of the dataset) and a testing dataset (one-third of the dataset). We used stepwise linear regression to identify the subset of variables that were most predictive. Next, we examined the correlation between measured and predicted percent MD in the testing dataset and computed the r2 in the total dataset. We used logistic regression to examine the association between measured and predicted percent MD and breast cancer risk. Results In the training dataset, several variables were selected for inclusion, including age, body mass index, and parity, among others. In the testing dataset, the Spearman correlation coefficient between predicted and measured percent MD was 0.61. As the prediction model performed well in the testing dataset, we developed the final model in the total dataset. The final prediction model explained 41% of the variability in percent MD. Both measured and predicted percent MD were similarly associated with breast cancer risk adjusting for age, menopausal status, and hormone use (OR per 5 unit increase=1.09 for both). Conclusion These results suggest that predicted percent MD may be useful for research studies in which mammograms are unavailable.

Automated percent mammographic density, mammographic texture variation, and risk of breast cancer: a nested case-control study

“…Film mammogram cranio-caudal (CC) views of each breast were digitized with a Lumysis 85 laser film scanner or a VIDAR CAD PRO Advantage scanner (VIDAR Systems Corporation, Herndon, VA, USA). The correlation between percent density measures from the two scanners was 0.88 36 . Cohort participants provided written informed consent.…”

Genome-wide and transcriptome-wide association studies of mammographic density phenotypes reveal novel loci

“…However, a few studies included in our study used the thresholding approach other than CUMULUS , which may cause inconsistency in the measurement of MD phenotypes and thus lead to biased results. Also, although previous studies have demonstrated that the MD measurement collected by CUMULUS was highly reproducible [ 8 , 46 ], it is important to acknowledge that it was a reader-dependent approach and thus might inevitably be subjective to measurement error. Another weakness with our study is the lack of diversity, as our study sample only included women of European ancestry.…”

Interactions of alcohol and postmenopausal hormone use in regards to mammographic breast density

“…These mammograms were scanned using both the Lumysis 85 laser scanner and the VIDAR CAD PRO Advantage scanner; percent density was measured by the same observer using Cumulus. The correlation between percent density as measured by the two scanners was 0.88; the mean difference was 2.3% points [41].…”