Abstract #2373

Comparison of breast BPE segmentation methods for early prediction of response to treatment

Alex Nguyen¹, Fredrik Strand², Vignesh Arasu¹, Wen Li¹, Natsuko Onishi¹, Jessica Gibbs¹, Bonnie N Joe¹, Laura J Esserman³, The I-SPY2 Investigator Network⁴, David C Newitt¹, and Nola M Hylton¹

¹Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA, United States, ²Department of Oncology and Pathology, Karolinska Institutet, Stockholm, Sweden, ³Department of Surgery, University of California, San Francisco, San Francisco, CA, United States, ⁴Quantum Leap Healthcare Collaborative, San Francisco, CA, United States

Breast parenchymal enhancement (BPE) has shown association with breast cancer risk and response to neoadjuvant treatment. However, BPE quantification is challenging and there is no agreed upon standard. This study compares the results of three fully automated segmentation methods for early prediction of pathologic complete response (pCR) following neoadjuvant treatment. We evaluated three different sub-volumes of interest segmented from DCE-MRI: full stack, half stack, and center 5 slices. The differences between methods were assessed and a univariate logistic regression model was implemented to determine predictive performance of each segmentation method.

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

Join Here