In this abstract, we show that the diagnosis accuracy of mild cognitive impairment (MCI) can be significantly improved by integrating dynamic information contained in the traditional functional connectivity (FC) from grey matter (GM) regions and the functional correlation tensors (FCT) from white matter (WM) regions, both computed from resting-state fMRI (RS-fMRI). The advantages of our method include: 1) dynamic FC is exploited to reveal rich time-varying information in FC, and 2) the anatomical structure information within WM can be well incorporated in RS-fMRI.
This abstract and the presentation materials are available to members only; a login is required.