Wen Li1, Rohan Nadkarni1, David C Newitt1, Bo La Yun1,2, Deep Hathi1, Alex Nguyen1, Natsuko Onishi1, Lisa J Wilmes1, Ella F Jones1, Jessica Gibbs1, Teffany Joy Bareng1, Bonnie N Joe1, Elissa Price1, Rita Mukhtar1, John Kornak1, Efstathios Gennatos1, I-SPY 2 Consortium3, Laura J Esserman1, and Nola M Hylton1
1University of California, San Francisco, San Francisco, CA, United States, 2Seoul National University Bundang Hospital, Seoul, Korea, Republic of, 3Quantum Leap Healthcare Collaborative, San Francisco, CA, United States
1University of California, San Francisco, San Francisco, CA, United States, 2Seoul National University Bundang Hospital, Seoul, Korea, Republic of, 3Quantum Leap Healthcare Collaborative, San Francisco, CA, United States
In the prediction of pathologic complete response of breast cancer in neoadjuvant setting, addition of radiomic shape features to FTV on MRI showed improvements in the performance over FTV alone, especially at the early treatment time point.
Fig. 4 AUCs for predicting pCR using logistic regression model at T0 (top) and T1 (bottom). The number of patients and pCR rate included in analysis at T0 were: 941 (35%), 368 (18%), 149 (39%), 81 (68%), 343 (43%) for full, HR+/HER2-, HR+/HER2+, HR-/HER2+, HR-/HER2- respectively. The numbers at T1 were: 904 (34%), 357 (18%), 142 (39%), 74 (66%), 331 (42%). FTV – functional tumor volume, HR – hormone receptor, HER2 – human epidermal growth factor receptor 2.
Fig. 3 Correlation map among FTV and shape features at T0.
