Does texture analysis classify semantic dementia from Alzheimer’s disease better than volumetric analysis?

Abstract

AbstractBackgroundTexture analysis may capture subtle changes in the gray matter more sensitively than volumetric analysis. We aimed to investigate the patterns of neurodegeneration in semantic dementia (SD) and Alzheimer’s disease (AD) by comparing the temporal gray matter texture and volume between cognitively normal controls and older adults with SD and AD.MethodWe enrolled all participants from three national university hospitals in Korea. We obtained T1‐weighted magnetic resonance images and compared the gray matter texture and volume of regions of interest (ROIs) between the groups using analysis of variance with Bonferroni posthoc comparisons. We also developed models for classifying SD, AD and control groups using logistic regression analyses, and validated the models using receiver operator characteristics analysis.ResultCompared to the AD group, the SD group showed lower volumes in five ROIs (bilateral temporal poles, and the left inferior, middle, and superior temporal cortices) and higher texture in these five ROIs and two additional ROIs (right inferior temporal and left entorhinal cortices). The performances of both texture‐ and volume‐based models were good and comparable in classifying SD from NC (mean area under the curve [AUC] = 0.914 for texture; mean AUC = 0.894 for volume). However, only the texture‐based model achieved a good level of performance in classifying SD and AD (mean AUC = 0.775 for texture; mean AUC = 0.658 for volume).ConclusionTexture may be a useful neuroimaging marker for early detection of SD in older adults and its differentiation from AD.