作者: Lei Wang , Ali Khan , John G. Csernansky , Bruce Fischl , Michael I. Miller
DOI: 10.1002/HIPO.20616
关键词:
摘要: Landmark-based high-dimensional diffeomorphic maps of the hippocampus (although accurate) is highly-dependent on rater’s anatomic knowledge in magnetic resonance images. It therefore vulnerable to rater drift and errors if substantial amount effort not spent quality assurance, training, re-training. A fully-automated, FreeSurfer-initialized large-deformation metric mapping procedure small brain substructures, including hippocampus, has been previously developed validated samples. In this report, we demonstrate that fully-automated pipeline can be used place landmark-based a large-sample clinical study produce similar statistical outcomes. Some direct comparisons two procedures are also presented.