Radiomic approach for predicting short-term postoperative recovery of cervical spondylotic myelopathy based on NODDI and T2*WI
Meng-Ze Zhang1, Han-Qiang Ou-Yang1,2,3, Chun-Jie Wang1, Jian-Fang Liu1, Dan Jin1, Xian-Chang Zhang4, Qiang Zhao1, Xiao-Guang Liu1,2,3, Zhong-Jun Liu1,2,3, Ning Lang1, Xing-Wen Sun1, Liang Jiang1,2,3, and Hui-Shu Yuan1
1Peking University Third Hospital, Beijing, China, 2Engineering Research Center of Bone and Joint Precision Medicine, Beijing, China, 3Beijing Key Laboratory of Spinal Disease Research, Beijing, China, 4MR Collaboration, Siemens Healthineers Ltd, Beijing, China
This study used radiomics based on T2*-weighted imaging (T2*WI) and neurite orientation dispersion and density imaging (NODDI) to predict the short-term recovery of patients with cervical spondylotic myelopathy (CSM). By classifying patients into good and poor outcomes based on the 3-month recovery rate, we found both T2*WI- and NODDI-based radiomic features to have good prognostic power. Furthermore, radiomic score based on NODDI was an independent predictor, whereas the other features were not. These findings suggest that radiomics based on NODDI has good prognostic power for CSM.
This abstract and the presentation materials are available to members only;
a login is required.