Abstract #2396

Radiomics based on multiparametric magnetic resonance imaging to predict extraprostatic extension of prostate cancer

Lili Xu¹, Gumuyang Zhang¹, Lun Zhao², Li Mao², Xiuli Li², Weigang Yan³, Yu Xiao⁴, Jing Lei¹, Zhengyu Jin¹, and Hao Sun¹

¹Department of Radiology, Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences, Beijing, China, ²Deepwise AI Lab, Beijing, China, ³Department of Urology, Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences, Beijing, China, ⁴Department of Pathology, Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences, Beijing, China

The preoperative prediction of EPE has a profound impact on treatment decision making, however, it still remains challenging presently. In this study, we compared the radiomics signatures extracted from different MR sequences to diagnose EPE. The radiomics signature based on DWI showed better performance for EPE prediction among mpMRI sequences. The radiomics model based on DWI, T2WI and DCE images was demonstrated feasible for the prediction of EPE. But the added value of clinical variables to the radiomics model was not prominent.

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

Join Here