Abstract #2471

Differentiation Between Intermingled and Central Type Breast Parenchymal Patterns Using Quantitative Morphological Parameters Based on Segmented Dense Tissue

Ke Nie¹, Jeon-Hor Chen^1,2, Daniel Chang¹, Chieh-Chih Hsu², Orhan Nalcioglu¹, Min-Ying Lydia Su¹

¹Tu & Yuen Center for Functional Onco-Imaging, University of California, Irvine, Irvine, CA, United States; ²Department of Radiology, China Medical University, Taichung, Taiwan

Breast parenchymal pattern is a well-known risk factor. The commonly used term breast density only measures the amount of breast tissue, not the relative distribution between the fat and fibroglandular tissue. In this study, we developed quantitative parameters to characterize different parenchymal distribution patterns (intermingled vs. central types) based on the segmented dense tissue on 3D MRI. In a dataset of 230 cases, the area under the ROC curve could reach to 0.94 using combined parameters. These features can be further used to investigate the relationship between parenchymal pattern and the cancer risk.