Meeting Banner
Abstract #4367

Multiparametric MRI Radiomic Signatures: Individual Prediction for Prostate Cancer and Benign lesions with same imaging findings

Min Xu1, Xiangming Fang1, Mengjie Fang2, Di Dong2, Jie Tian2, and Zhongshuai Zhang3

1Imaging Center, Wuxi People’s Hospital, Nanjing Medical University, Wuxi, China, 2CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing P.R. China; University of Chinese Academy of Sciences, Beijing P.R. China., Beijing, China, 3Siemens Healthcare Ltd., Shanghai, China

Quantitative Radiomic features based on multiparametric Magnetic Resonance Imaging have great clinical value in discriminating prostate cancer and benign lesions with same imaging findings. We extracted Radiomic features and compared the discrimination efficiency of the combined three types of images with each single type of images, then incorporated independent clinical risk factors and further developed an individual prediction model. The experimental results show that the individual prediction model achieved more accurate diagnosis results than only using Radiomic signatures or clinical factors

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

Join Here