Exploring reliable biomarkers is important for the clinical early detection of mild cognitive impairment (MCI) patients . This study investigated cerebral morphological abnormalities in MCI by combining three widely-used morphometry analysis methods (Voxel-based morphometry (VBM), deformation-based morphometry (DBM) and surface-based morphometry (SBM)) and constructed a set of classifiers to identify MCI patients from normal controls. The highest classification accuracy (91%) was reached when using combined morphological features (including gray matter volume, deformation, cortex thickness, gyrification index, sulcus depth and fractal dimension). Our results indicate that using combined morphological features could improve the performance of MCI prediction compared to using a single morphometry method
This abstract and the presentation materials are available to members only; a login is required.