This study explores the prediction of pathologic complete response (pCR) using tumor-derived textural features in breast cancer patients receiving neoadjuvant chemotherapy. Textural features were generated from increasingly restricted tumor masks applied on DCE-MRI signal enhancement ratio maps. Elastic net and random forests models were trained on features from baseline and early treatment timepoints, resulting in minimal differences in AUC between percent enhancement segmentation thresholds and a mean AUC of 0.68 (range 0.60-0.75). Our analysis suggests that, for the prediction of pCR, textural features derived from strongly enhancing regions dominate over those from regions of lower enhancement.
This abstract and the presentation materials are available to members only; a login is required.