The Effects of White Matter Disease on the Automated Brain Segmentation in an Alzheimer's Disease Population

• Activity Number: 58 - Neuroimaging Statistics for Aging and Dementia Studies
• Type: Topic Contributed
• Date/Time: Sunday, July 30, 2017 : 4:00 PM to 5:50 PM
• Sponsor: Biometrics Section
• Author(s): Dana Tudorascu* and Helmet Karim and Lea Alhilali and Oscar Lopez and Howard Aizenstein and Bill Klunk and Ciprian M Crainiceanu
• Companies: and University of Pittsburgh and Barrow Neurological Institute, and University of Pittsburgh and University of Pittsburgh and University of Pittsburgh and Johns Hopkins University
• Keywords: MRI segmentation ; white matter hyper intensities ; Alzheimer's disease ; longitudinal studies of MRI

Abstract

Automated segmentation of the brain is a challenging task in the presence of brain pathologies such as white matter hyperintensities (WMH). WMHs appear as hyperintense areas in magnetic resonance imaging (MRI) and are frequently found in Alzheimer's disease (AD) population's brain. WMHs present a challenge for standard segmentation algorithms that misclassify WMHs as gray matter (GM). A cross-sectional and longitudinal study of AD population conducted at our institution was used to demonstrate the effect of WMH on brain segmentation and normalization. An automated algorithm was first used to detect WMH that were later filled with normal-appearing white-matter (NAWM) intensities. The filled MRI scans were then segmented again and the resulting gray matter volume was compared with that computed from a standard and a multispectral segmentation approach. Repeated measures models, intraclass correlation coefficients and neurological case studies were used for the analyses. The presence of WMH affected the segmentations for both, cross-sectional and longitudinal sample suggesting that studies investigating structural differences in populations with high WMH should account for WMH.