Purpose: Previous studies showed voxel-based volumetry as a helpful tool in detecting pathologic brain atrophy. Aim of this study was to investigate whether the inclusion of CSF volume improves the imaging based diagnostic accuracy using combined automated voxel- and region-based volumetry.
Methods: In total, 120 individuals (30 healthy elderly, 30 frontotemporal dementia (FTD), 30 Alzheimer's dementia (AD) and 30 Lewy body dementia (LBD) patients) were analyzed with voxel-based morphometry and compared to a reference group of 360 healthy elderly controls. Abnormal GM and CSF volumes were visualized via z-scores. Volumetric results were finally evaluated by ROC analyses.
Results: Based on the volume of abnormal GM and CSF voxels high accuracy was shown in separating dementia from normal ageing (AUC 0.93 and 0.91, respectively) within 5 different brain regions per hemisphere (frontal, medial temporal, temporal, parietal, occipital). Accuracy for separating FTD and AD was higher based on CSF volume (FTD: AUC 0.80 vs. 0.75 in frontal regions; AD: AUC 0.78 vs. 0.68 in parietal regions based on CSF and GM respectively).
Conclusions: Differentiation of dementia patients from normal ageing persons shows high accuracy when based on automatic volumetry alone. Evaluating volumes of abnormal CSF performed better than volumes of abnormal GM, especially in AD and FTD patients.
Keywords: Alzheimer’s disease; Dementia; Frontotemporal dementia; Lewy body dementia; Machine learning; Volumetry.
Copyright © 2020 The Authors. Published by Elsevier B.V. All rights reserved.