Meeting Banner
Abstract #2748

MRI-based radiomics signature for head and neck squamous cell carcinoma patients

Ling Dong1, Ying Yuan2, Xiaofeng Tao2, Di Dong3, Zhenyu Liu3, Yali Zang3, and Jie Tian4

1University of Electronic Science and Technology of China, Beijing, China, 2Shanghai Ninth People’s Hospital, Shanghai, China, 3CAS 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, 4CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China

To assess overall survival (OS) of head and neck squamous cell carcinoma (HNSCC) patients and the radiomics features, a large number of quantitative radiomics features were extracted from MRI and selected by machine learning methods. Based on these features, a multivariate Cox proportional hazards model was built as a independent predictor to identify patients. Seven features was found to have association with OS (training cohort, P < 0.0001; testing cohort, P = 0.0013). In the training cohort, the radiomics signature yielded a C-index of 0.73 (95% CI, 0.63-0.84), which was 0.71 (95% CI: 0.59-0.82) in the testing cohort. The potential association between MRI-based radiomics signature and OS was explored.

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

Join Here

Abstract