Meeting Banner
Abstract #5474

A support vector machine-based method to identify  non-neuropsychiatric systemic lupus erythematosus  with Regional Homogeneity

Xiangliang Tan1, Zhuqing Long2, Yingjie Mei3, Wenjun Qiao1, Kai Han4, and Yikai Xu1

1Medical Imaging Center, Nanfang Hospital, Southern Medical University, Guangzhou, China, 2Medical apparatus and equipment deployment, Nanfang Hospital, Southern Medical University, Guangzhou, China, 3Philips Healthcare, Guangzhou, China, 4Department of Dermatology, Nanfang Hospital, Southern Medical University, Guangzhou, China

Previous studies found that changes in brain function happened in default mode network beforeNeuropsychiatric involvement (NPSLE) development by using resting-state functional magnetic resonance imaging (rs-fMRI), highlighting the need for early evaluation and intervention in SLE patients. In this study, we proposed a valid Support Vector Machine (SVM) -based method to identify non-NPSLE using regional homogeneity (ReHo). The results demonstrate that ReHo parameter is an effective classification feature for the SVM-based method to identify SLE patients from healthy subjects.

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

Join Here