Radiomics of Voxel-Wise DCE-MRI Wash-In and Wash-Out Maps Enable Quantitative Assessment of Hemodynamic Heterogeneity within Breast Lesions

Motivation: Tumor hemodynamic heterogeneity offers potential for characterizing, diagnosing, and prognosticating breast lesions. Current methods primarily address either spatial morphological heterogeneity or temporal aspects. Goal(s): This study aims to develop a method that visualizes and quantifies both temporal and spatial hemodynamic heterogeneity simultaneously to enhance breast lesion management. Approach: We propose generating voxel-wise time-intensity curve (TIC) corresponding wash-in and wash-out parameter maps to visualize the spatial distribution of temporal information. Radiomics is then used to extract features that quantify hemodynamic heterogeneity. Results: The study successfully demonstrated the clinical utility (AUC = 0.9846) of these quantitative features in differentiating benign from malignant lesions. Impact: This novel approach provides an intuitive and self-explainable visualization and quantification of spatial and temporal hemodynamic heterogeneity, with potential applications across a broader range of clinical settings.