MRI-based hippocampus volume, a core feasible biomarker of Alzheimer's disease (AD), is not yet widely used in clinical patient care, partly due to lack of validation of software tools for hippocampal volumetry that are compatible with routine workflow. Here, we evaluate fully-automated and computationally efficient hippocampal volumetry with FSL-FIRST for prediction of AD dementia (ADD) in subjects with amnestic mild cognitive impairment (aMCI) from phase 1 of the Alzheimer's Disease Neuroimaging Initiative. Receiver operating characteristic analysis of FSL-FIRST hippocampal volume (corrected for head size and age) revealed an area under the curve of 0.79, 0.70, and 0.70 for prediction of aMCI-to-ADD conversion within 12, 24, or 36 months, respectively. Thus, FSL-FIRST provides about the same power for prediction of progression to ADD in aMCI as other volumetry methods.
Keywords: ADNI; Alzheimer’s disease; FSL-FIRST; aMCI-to-Alzheimer’s disease dementia conversion; amnestic mild cognitive impairment; fully-automated; hippocampal volumetry; magnetic resonance imaging; model-based segmentation; prediction.