In:
Cerebral Cortex, Oxford University Press (OUP), Vol. 32, No. 21 ( 2022-10-20), p. 4641-4656
Abstract:
Subcortical ischemic vascular disease could induce subcortical vascular cognitive impairments (SVCIs), such as amnestic mild cognitive impairment (aMCI) and non-amnestic MCI (naMCI), or sometimes no cognitive impairment (NCI). Previous SVCI studies focused on focal structural lesions such as lacunes and microbleeds, while the functional connectivity networks (FCNs) from functional magnetic resonance imaging are drawing increasing attentions. Considering remarkable variations in structural lesion sizes, we expect that seeking abnormalities in the multiscale hierarchy of brain FCNs could be more informative to differentiate SVCI patients with varied outcomes (NCI, aMCI, and naMCI). Driven by this hypothesis, we first build FCNs based on the atlases at multiple spatial scales for group comparisons and found distributed FCN differences across different spatial scales. We then verify that combining multiscale features in a prediction model could improve differentiation accuracy among NCI, aMCI, and naMCI. Furthermore, we propose a graph convolutional network to integrate the naturally emerged multiscale features based on the brain network hierarchy, which significantly outperforms all other competing methods. In addition, the predictive features derived from our method consistently emphasize the limbic network in identifying aMCI across the different scales. The proposed analysis provides a better understanding of SVCI and may benefit its clinical diagnosis.
Type of Medium:
Online Resource
ISSN:
1047-3211
,
1460-2199
DOI:
10.1093/cercor/bhab507
Language:
English
Publisher:
Oxford University Press (OUP)
Publication Date:
2022
detail.hit.zdb_id:
1483485-6
SSG:
12
Bookmarklink