The purpose of this study was to investigate how background parenchymal enhancement (BPE) may additively improve an MR tumor model for prediction of non-pathologic complete response (non-PCR) patients in the neoadjuvant setting. BPE identified 24-36% of non-PCR patients independent of tumor factors while maintaining a low misclassification of PCR patients. In conjunction with a tumor model using tumor and treatment factors, addition of BPE may improve residual cancer prediction of up to 60% of patients, but results were not statistically significant.
This abstract and the presentation materials are available to members only; a login is required.