Model-free group analysis shows altered BOLD FMRI networks in dementia

Abstract

FMRI research in Alzheimer's disease (AD) and mild cognitive impairment (MCI) typically is aimed at determining regional changes in brain function, most commonly by creating a model of the expected BOLD-response and estimating its magnitude using a general linear model (GLM) analysis. This crucially depends on the suitability of the temporal assumptions of the model and on assumptions about normality of group distributions. Exploratory data analysis techniques such as independent component analysis (ICA) do not depend on these assumptions and are able to detect unknown, yet structured spatiotemporal processes in neuroimaging data. Tensorial probabilistic ICA (T-PICA) is a model free technique that can be used for analyzing multiple subjects and groups, extracting signals of interest (components) in the spatial, temporal, and also subject domain of FMRI data. We applied T-PICA and model-based GLM to study FMRI signal during face encoding in 18 AD, 28 MCI patients, and 41 healthy elderly controls. T-PICA showed activation in regions associated with motor, visual, and cognitive processing, and deactivation in the default mode network. Six networks showed a significantly decreased response in patients. For two networks the T-PICA technique was significantly more sensitive to detect group differences than the standard model-based technique. We conclude that T-PICA is a promising tool to identify and detect differences in (de)activated brain networks in elderly controls and dementia patients. The technique is more sensitive than the commonly applied model-based method. Consistent with other research, we show that networks of activation and deactivation show decreased reactivity in dementia.

Figure 1

Selection of spatial modes of grey matter, resulting from the model‐free analysis in all 86 subjects together. The displayed (thresholded) voxel values are from the vectors of matrix B in formula (1): for each component, the vectors represent the voxel values. Spatial mode A contains mainly left middle and superior frontal regions and parietal regions. (B) contains the auditory system; (C) includes the right frontal and parietal regions (complementary to A), and also the thalamus, insula, caudate nucleus, and hippocampus (most of these included regions are not displayed in the figure; (D) contains the left motor cortex and thalamus; (E) contains medial visual regions and caudate nucleus, putamen, and hippocampus; (F) includes lateral visual regions; (G,H) include medial frontal regions, anterior and posterior cingulum, bilateral parietal cortex, parahippocampal gyrus bilateral, precuneus. (G) contains mainly anterior regions, (H) mainly posterior regions. (A,B) show no significant difference between patients and controls, (C–H) show a significantly diminished BOLD response in patients (see figure 2). Red–yellow: activation positively correlated with the paradigm. Blue: signal negatively correlated with the paradigm (“deactivation”). Colors are scaled ranging from minimum to maximum separately in each mode. The coordinates refer to millimeter distance from the anterior commissure in MNI space and images are shown in radiological convention (left in image is right in brain).

Figure 2

Time courses (time domain, top) and boxplots of values in the subject domain (bottom) corresponding to the eight spatial modes shown in Figure 1. The time courses are the values of the vectors of matrix A in formula (1), the subject domain numbers are the values of the vectors in matrix C. In the subject domain, the boxplots show the distribution of regression values for each group separately to illustrate the group differences of spatial networks C–H. There were no group differences for the spatial networks A and B. [Color figure can be viewed in the online issue, which is available at www.interscience.wiley.com.]