Abstract #2271

Radiomics Features Extracted from MRI as Biomarkers for Neuromyelitis Optica Spectrum Disorder and Multiple Sclerosis Differentiation

Xiaoxiao Ma¹, Mengjie Fang², Jun Yang³, Jinhao Lyu¹, Xin Li³, Deihui Huang⁴, Di Dong², Lin Ma¹, and Xin Lou¹

¹Department of Radiology, Chinese PLA General Hospital, Beijing, People's Republic of China, ²Chinese Academy of Sciences, Beijing, People's Republic of China, ³GE healthcare, Shanghai, People's Republic of China, ⁴Department of Neurology, Chinese PLA General Hospital, Beijing, People's Republic of China

The aim of our study was to ultilize combined radiomcis features extracted from T2-weighted MRI images as quantitative imaging biomarkers to differentiate neuromyelitis optica spectrum disorder (NMOSD) and multiple sclerosis (MS). Twenty-nine NMOSD patients and forty-five MS patients were enrolled. Our study showed 61 radiomics features and 8-feature-based radiomics signature were significantly different between NMOSD and MS. Therefore, radiomics may be an newly useful method which provides a promising non-invasive way of differentiating NMOSD and MS.

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

Join Here