TY  - JOUR
AU  - Liang, Yuan
AU  - Zheng, Yu
AU  - Renli, Brighty
AU  - Zhu, David C.
AU  - Yu, Fang
AU  - Li, Tongtong
PY  - 2020
DA  - 2020/06/01
TI  - Dynamic Functional Connectivity Fading Analysis and Classification of Alzheimer’s Disease, Mild Cognitive Impairment and Normal Control Subjects based on Resting-State fMRI Data
JO  - OBM Neurobiology
SP  - 059
VL  - 04
IS  - 02
AB  - In this paper, motivated by the fading effect in wireless communications, where severe channel fading is related to information loss during the transmission, we evaluate and analyze the fading effect in time-varying functional connectivity of AD, MCI and NC subjects based on the resting-state fMRI data, and then apply that for AD, MCI, NC classification. We show that in some critical brain regions, compared with NC subjects, AD subjects suffer more severe and long lasting fading in the functional connectivity level; in other words, AD subjects show selective loss in the amount of information successfully exchanged between the brain regions. On the other hand, MCI subjects experience less severe and shorter fading in functional connectivity level in general, and the connectivity level of MCI may be tangled together with that of either NC or AD. The underlying neurobiological basis for the possible information loss during the transmission process in AD is that the most vulnerable neurons in AD are the association neurons with long projections that formulate the communication channels or links between the brain regions, and these vulnerable neurons often suffer from loss of dendrites that leads to a significant impairment of synaptic transmission. We also show that, compared with static network connectivity pattern analysis that extracts only the region-level spatial variability, dynamic network connectivity pattern analysis, which exploits both the temporal and spatial variability in functional connectivity, can achieve much higher accuracy in the classification of AD, MCI and NC. When the AD, MCI and NC subjects are all mixed together, the prediction accuracy of time-varying connectivity based classification is 90.9%, 75.0% and 80.0% for NC, MCI and AD, respectively. Our result is consistent with existing results on dynamic functional connectivity analysis for AD and MCI.
SN  - 2573-4407
UR  - https://doi.org/10.21926/obm.neurobiol.2002059
DO  - 10.21926/obm.neurobiol.2002059
ID  - Liang2020
ER  -