Meeting Banner
Abstract #1629

Radiomics based on Multiparametric MRI for Predicting Upgrading of Prostate Cancer from Biopsy to Radical Prostatectomy

Gumuyang Zhang1, Yuqi Han2,3, Jingwei Wei3, Yafei Qi1, Dongsheng Gu3, Jing Lei1, Yu Xiao1, Weigang Yan1, Huadan Xue1, Feng Feng1, Hao Sun1, Zhengyu Jin1, and Jie Tian3

1Peking Union Medical College Hospital, Beijing, China, 2School of Life Science and Technology, Xidian University, Xi'an, China, 3Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China

The disparity of biopsy Gleason score of prostate cancer (PCa) with that of the corresponding radical prostatectomy (RP) remains an unsolved problem. We developed and validated radiomics model based on T2-weighted, fat-suppressed T2W, apparent diffusion coefficient and dynamic contrast enhancement images to predict upgrading from biopsy to RP. The radiomics model achieved the area under the curve values of 0.977 and 0.931 for the training and validation cohorts, and outperformed the clinical model combining clinical stage and time from biopsy to RP. The radiomics model could serve as a non-invasive tool for individualized prediction of upgrading of PCa.

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

Join Here