Digital Breast Tomosynthesis Parenchymal Texture Analysis for Breast Cancer Risk Estimation: A Preliminary Study

Abstract

Studies with mammograms have demonstrated a relationship between parenchymal texture and breast cancer risk. Although promising, texture analysis in mammograms is limited by the effect of tissue superimposition. Digital Breast Tomosynthesis (DBT) is a novel tomographic x-ray breast imaging modality that alleviates the effect of tissue superimposition. We explore the potential advantages of DBT texture analysis for breast cancer risk estimation. We analyzed bilateral DBT and DM images from 39 women, and compared the performance of the computed texture features in (i) reflecting characteristic parenchymal properties, and (ii) correlating to mammographic breast density, an established surrogate of breast cancer risk. Strong texture correlation was observed between contralateral and ipsilateral breasts, indicating that parenchymal properties are potentially inherent to an individual woman. Compared to DM, DBT texture features demonstrated a stronger correlation with breast density. Although preliminary, our results show that DBT texture analysis could potentially improve breast cancer risk estimation.