Beck, Andrew

Abstract Background: This analysis aimed to determine if associations of prediagnostic mammographic percent breast density, absolute dense area, and absolute non-dense area and risk of breast cancer vary according to the subsequent breast tumors biomarker status. Methods: We included 1,154 postmenopausal women diagnosed with breast cancer between June 1, 1989, and June 30, 2004, and 2,078 matched controls from the Nurses' Health Study I and II. Percent breast density, absolute dense and non-dense areas were estimated from digitized film mammograms using computer assisted thresholding techniques. Density measures were modeled as quartiles. Information on estrogen receptor (ESR1 [ER]), progesterone receptor (PGR [PR]), and human epidermal growth factor receptor 2 (ERBB2 [HER2]) status was obtained from pathology reports and medical records, and if missing, from immunostains performed on paraffin sections of tumor tissue microarrays (TMAs). Other biomarkers assessed on TMAs were androgen receptor (AR), cytokines 5/6 (KRT5/KRT6 [CK5/6]), epidermal growth factor receptor (EGFR), vascular endothelial growth factor (VEGFA [VEGF]), and cyclooxygenase 2 (PTGS2 [COX2]). Information on breast cancer risk factors was obtained prospectively from biennial questionnaires before the date of cancer diagnosis for cases and matched controls. Polychotomous logistic regression was used to assess associations of the three breast density measures with tumor subtypes based on the status of selected tissue markers. Results: Breast cancer risk was positively associated with percent density and absolute dense area and inversely associated with absolute non-dense area (p for trend<0.0001 for all). The associations of percent density with breast cancer risk did not statistically significantly differ by the status of any of the markers. However, we found stronger positive associations for absolute dense area and KRT5/KRT6- and EGFR- tumors as compared to respective marker-positive tumors (4th vs. 1st quartile: OR=2.99 for KRT5/KRT6- vs. OR=0.92 for KRT5/KRT6+ tumors, p-heterogeneity <0.001; OR=3.06 for EGFR- vs. OR=1.08 for EGFR+ tumors, p-heterogeneity=0.001). Stronger inverse associations of absolute non-dense area with breast cancer risk were found for ESR1- as compared to ESR1+ tumors, and for AR+, KRT5/KRT6+, and EGFR+ tumors as compared to respective marker-negative tumors (4th vs. 1st quartile: OR=0.21 for ESR1- vs. OR=0.59 for ESR1+ tumors, p-heterogeneity <0.0001; OR=0.22 for AR+ vs. OR=0.42 for AR- tumors, p-heterogeneity=0.04; OR=0.21 for KRT5/KRT6+ vs. OR=1.14 for KRT5/KRT6- tumors, p-heterogeneity<0.01; OR=0.37 for EGFR+ vs. OR=1.11 for EGFR- tumors, p-heterogeneity<0.01). There were no differences in associations of the density measures with breast cancer by status of other markers evaluated. Conclusions: The findings suggest that some mammographic density measures are differentially associated with the risk of subsequent breast tumor subtypes. Citation Format: Lusine Yaghjyan, Andreas Pettersson, Graham Colditz, Laura Collins, Stuart Schnitt, Andrew Beck, Bernard Rosner, Celine Vachon, Rulla Tamimi. Mammographic breast density and subsequent risk of breast cancer in postmenopausal women according to the status of selected tissue markers: A case-control study. [abstract]. In: Proceedings of the Twelfth Annual AACR International Conference on Frontiers in Cancer Prevention Research; 2013 Oct 27-30; National Harbor, MD. Philadelphia (PA): AACR; Can Prev Res 2013;6(11 Suppl): Abstract nr PR09.

Abstract Background: High percent mammographic density (MD), which reflects the relative fibroglandular tissue content of the breast, is one of the strongest breast cancer risk factors; however, the pathologic mediators of this risk are unknown. We hypothesize that analysis of breast tissue sections using deep learning approaches may characterize histologic features that underpin risk associated with high MD. Methods: Non-targeted H&E stained breast tissue sections of diagnostic image-guided breast biopsies were evaluated among 588 women enrolled following an abnormal mammogram in the Breast Radiology Evaluation and Study of Tissues (BREAST) Stamp Project (2007-2010). Overall volumetric percent MD for the biopsied breast and localized volumetric percent MD surrounding the biopsy site were determined for each participant. A deep convolutional neural network (CNN) model was trained to identify and quantitatively assess breast epithelial, stroma and fat tissue and their organizational and spatial arrangements. Least absolute shrinkage and selection operator (Lasso) regression was used to determine relationships between MD measures and pathological features. To ensure reliability of the model, a cross-validation strategy was employed to build and assess the performance of the fitted model. Finally, Spearman correlation coefficients were estimated to test the association between the predicted density values by each model (predicting overall or localized MD) and the actual MD measurements. We report the average and standard deviation (SD) of the correlation coefficients. Results: In an independent validation set, the CNN model was 95.5% accurate in classifying epithelial, stromal and fat tissue. The mean (SD) correlations between the predicted model and the actual measurements for overall and localized MD were 0.70 (0.06) and 0.65 (0.06) respectively. The amount of stroma identified (normalized to tissue area) had the highest selection probability (P-value) by the Lasso model and thus the strongest positive relationship with MD (P-value >0.9 for each MD measurement). In contrast, the amount of normalized epithelial tissue was not related to MD (P-value=0.01 for each MD measurement). No association was observed for the total normalized fat area with MD (P-value <0.31 for each MD measurement). In addition, the number of distributed epithelial regions was positively associated, whereas the distance between epithelial regions was inversely associated with overall MD (P-value <0.87 and 0.62, respectively). Conclusions: These results show that greater stromal tissue amount and spatial distribution patterns of epithelial regions, rather than total epithelial amounts, had the strongest relationships with elevated MD. Future work will determine the relationship of these MD features with biopsy diagnosis. Citation Format: Maeve Mullooly, Babak Ehteshami Bejnordi, Maya Palakal, Pamela M. Vacek, Donald L. Weaver, John A. Shepherd, Bo Fan, Amir Pasha Mahmoudzadeh, Jeff Wang, Jason M. Johnson, Sally D. Herschorn, Brian L. Sprague, Ruth M. Pfeiffer, Louise A. Brinton, Mark E. Sherman, Andrew Beck, Gretchen L. Gierach. Application of convolutional neural networks to breast biopsies to uncover tissue correlates of mammographic breast density [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2017; 2017 Apr 1-5; Washington, DC. Philadelphia (PA): AACR; Cancer Res 2017;77(13 Suppl):Abstract nr 4235. doi:10.1158/1538-7445.AM2017-4235