Meeting Banner
Abstract #2341

Comparison of DCE-MRI Parametric Map-Based Features for Early Prediction of Breast Cancer Therapy Response

Archana Machireddy1, Guillaume Thibault1, Alina Tudorica1, Aneela Afzal1, May Mishal1, Kathleen Kemmer1, Arpana Naik1, Megan Troxell1, Eric Goranson1, Karen Oh1, Nicole Roy1, Neda Jafarian1, Megan Holtorf1, Wei Huang1, and Xubo Song1

1Oregon Health and Science University, Portland, OR, United States

DCE-MRI data from 55 breast cancer patients collected before and after the first cycle of neoadjuvant chemotherapy were subjected to pharmacokinetic analysis. Four texture features, GLCM, RLM, single- and multi-resolution fractals extracted from DCE-MRI parametric maps, were analyzed for early prediction of therapy response. Generally, the multi-resolution fractal features from individual maps or the concatenated features from all parametric maps showed better predictive performance. The results suggest that multi-resolution analysis, which decomposes the texture at various spatial-frequency scales, may more accurately capture changes in tumor vascular heterogeneity as measured by DCE-MRI, and thus provide better early prediction of therapy response.

This abstract and the presentation materials are available to members only; a login is required.

Join Here