scholarly journals Group Similarity Constraint Functional Brain Network Estimation for Mild Cognitive Impairment Classification

2020 ◽  
Vol 14 ◽  
Author(s):  
Xin Gao ◽  
Xiaowen Xu ◽  
Xuyun Hua ◽  
Peijun Wang ◽  
Weikai Li ◽  
...  
Keyword(s):  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Brain Network ◽  
Functional Brain ◽  
Functional Brain Network ◽  
Network Estimation ◽  
Group Similarity

scholarly journals Functional Hubs in Mild Cognitive Impairment

2015 ◽  
Vol 25 (03) ◽  
pp. 1550034 ◽  
Author(s):  
Adrián Navas ◽  
David Papo ◽  
Stefano Boccaletti ◽  
F. Del-Pozo ◽  
Ricardo Bajo ◽  
...  
Keyword(s):  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Short Term Memory ◽  
Brain Networks ◽  
Memory Task ◽  
Brain Network ◽  
Control Group ◽  
Functional Brain ◽  
Functional Brain Network ◽  
Functional Brain Networks

We investigate how hubs of functional brain networks are modified as a result of mild cognitive impairment (MCI), a condition causing a slight but noticeable decline in cognitive abilities, which sometimes precedes the onset of Alzheimer's disease. We used magnetoencephalography (MEG) to investigate the functional brain networks of a group of patients suffering from MCI and a control group of healthy subjects, during the execution of a short-term memory task. Couplings between brain sites were evaluated using synchronization likelihood, from which a network of functional interdependencies was constructed and the centrality, i.e. importance, of their nodes was quantified. The results showed that, with respect to healthy controls, MCI patients were associated with decreases and increases in hub centrality respectively in occipital and central scalp regions, supporting the hypothesis that MCI modifies functional brain network topology, leading to more random structures.

scholarly journals Topological Abnormalities of Functional Brain Network in Early-Stage Parkinson’s Disease Patients With Mild Cognitive Impairment

2020 ◽  
Vol 14 ◽  
Author(s):  
Xiangbin Chen ◽  
Mengting Liu ◽  
Zhibing Wu ◽  
Hao Cheng
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Information Exchange ◽  
Early Stage ◽  
Brain Network ◽  
Clustering Coefficient ◽  
Functional Brain ◽  
Functional Brain Network

Recent studies have demonstrated structural and functional alterations in Parkinson’s disease (PD) with mild cognitive impairment (MCI). However, the topological patterns of functional brain networks in newly diagnosed PD patients with MCI are unclear so far. In this study, we used functional magnetic resonance imaging (fMRI) and graph theory approaches to explore the functional brain network in 45 PD patients with MCI (PD-MCI), 22 PD patients without MCI (PD-nMCI), and 18 healthy controls (HC). We found that the PD-MCI, PD-nMCI, and HC groups exhibited a small-world architecture in the functional brain network. However, early-stage PD-MCI patients had decreased clustering coefficient, increased characteristic path length, and changed nodal centrality in the default mode network (DMN), control network (CN), somatomotor network (SMN), and visual network (VN), which might contribute to factors for MCI symptoms in PD patients. Our results demonstrated that PD-MCI patients were associated with disrupted topological organization in the functional network, thus providing a topological network insight into the role of information exchange in the underlying development of MCI symptoms in PD patients.

scholarly journals Group Similarity Constraint Functional Brain Network Estimation for Mild Congititive Impairment Classification

2019 ◽  
Author(s):  
Xin Gao ◽  
Xiaowen Xu ◽  
Weikai Li ◽  
Rui Li
Keyword(s):  
Poor Quality ◽  
Brain Network ◽  
Estimation Model ◽  
Activation Patterns ◽  
Functional Brain ◽  
Functional Brain Network ◽  
Network Estimation ◽  
Post Hoc ◽  
Group Similarity

AbstractFunctional brain network (FBN) provides an effective biomarker for understanding brain activation patterns, which also improve the diagnostic criteria for neurodegenerative diseases or the information transmission of brain. Unfortunately, despite its efficiency, FBN still suffers several challenges for accurately estimate the biological meaningful or discriminative FBNs, under the poor quality of functional magnetic resonance imaging (fMRI) data as well as the limited understanding of human brain. Hence, there still a motivation to alleviate those issues above, it is currently still an open field to discover. In this paper, a novel FBN estimation model based on group similarity constraints is proposed. In particular, we extend the FBN estimation model to the tensor form and incorporate the trace-norm regularizer for formulating the group similarity constraint. In order to verify the proposed method, we conduct experiments on identifying Mild Cognitive Impairments (MCIs) from normal controls (NCs) based on the estimated FBNs. The experimental results illustrated that the proposed method can construct a more discriminative brain network. Consequently, we achieved an 91.97% classification accuracy which outperforms the baseline methods. The post hoc analysis further shown more biologically meaningful functional brain connections obtained by our proposed method.

scholarly journals Gaussian embedding-based functional brain connectomic analysis for amnestic mild cognitive impairment patients with cognitive training

2019 ◽  
Author(s):  
Mengjia Xu ◽  
Zhijiang Wang ◽  
Haifeng Zhang ◽  
Dimitrios Pantazis ◽  
Huali Wang ◽  
...  
Keyword(s):  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Early Stage ◽  
Brain Networks ◽  
Disease Diagnosis ◽  
Brain Regions ◽  
Brain Network ◽  
Amnestic Mild Cognitive Impairment ◽  
Functional Brain ◽  
Functional Brain Network

AbstractIdentifying heterogeneous cognitive impairment markers at an early stage is vital for Alzheimer’s disease diagnosis. However, due to complex and uncertain brain connectivity features in the cognitive domains, it remains challenging to quantify functional brain connectomic changes during non-pharmacological interventions for amnestic mild cognitive impairment (aMCI) patients. We present a new quantitative functional brain network analysis of fMRI data based on the multi-graph unsupervised Gaussian embedding method (MG2G). This neural network-based model can effectively learn low-dimensional Gaussian distributions from the original high-dimensional sparse functional brain networks, quantify uncertainties in link prediction, and discover the intrinsic dimensionality of brain networks. Using the Wasserstein distance to measure probabilistic changes, we discovered that brain regions in the default mode network and somatosensory/somatomotor hand, fronto-parietal task control, memory retrieval, and visual and dorsal attention systems had relatively large variations during non-pharmacological training, which might provide distinct biomarkers for fine-grained monitoring of aMCI cognitive alteration.

scholarly journals Towards a Better Estimation of Functional Brain Network for Mild Cognitive Impairment Identification: A Transfer Learning View

2019 ◽  
Author(s):  
Weikai Li ◽  
Limei Zhang ◽  
Lishan Qiao ◽  
Dinggang Shen
Keyword(s):  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Transfer Learning ◽  
Brain Network ◽  
Quality Data ◽  
Imaging Biomarkers ◽  
Target Domain ◽  
High Quality ◽  
Functional Brain ◽  
Functional Brain Network

AbstractMild cognitive impairment (MCI) is an intermediate stage of brain cognitive decline, associated with increasing risk of developing Alzheimer’s disease (AD). It is believed that early treatment of MCI could slow down the progression of AD, and functional brain network (FBN) could provide potential imaging biomarkers for MCI diagnosis and response to treatment. However, there are still some challenges to estimate a “good” FBN, particularly due to the poor quality and limited quantity of functional magnetic resonance imaging (fMRI) data from the target domain (i.e., MCI study). Inspired by the idea of transfer learning, we attempt to transfer information in high-quality data from source domain (e.g., human connectome project in this paper) into the target domain towards a better FBN estimation, and propose a novel method, namely NERTL (Network Estimation via Regularized Transfer Learning). Specifically, we first construct a high-quality network “template” based on the source data, and then use the template to guide or constrain the target of FBN estimation by a weighted l1-norm regularizer. Finally, we conduct experiments to identify subjects with MCI from normal controls (NCs) based on the estimated FBNs. Despite its simplicity, our proposed method is more effective than the baseline methods in modeling discriminative FBNs, as demonstrated by the superior MCI classification accuracy of 82.4% and the area under curve (AUC) of 0.910.

Sign in / Sign up

Export Citation Format

Share Document