Meeting Banner
Abstract #0143

Effect of enhancement segmentation thresholds on predicting neoadjuvant response in breast cancer patients using DCE-MRI textural features

Deep K Hathi1, Rohan Nadkarni1, Natsuko Onishi1, Alex Anh-Tu Nguyen1, Wen Li1, Efstathios D Gennatas2, Bonnie N Joe1, Elissa R Price1, I-SPY 2 Consortium3, David C Newitt1, Ella F Jones1, and Nola M Hylton1
1Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, CA, United States, 2Epidemiology & Biostatistics, University of California San Francisco, San Francisco, CA, United States, 3Quantum Leap Healthcare Collaborative, San Francisco, CA, United States

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.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.

Keywords