Functional Connectivity Network Analysis with Discriminative Hub Detection for Brain Disease Identification

Abstract

Brain network analysis can help reveal the pathological basis of neurological disorders and facilitate automated diagnosis of brain diseases, by exploring connectivity patterns in the human brain. Effectively representing the brain network has always been the fundamental task of computeraided brain network analysis. Previous studies typically utilize human-engineered features to represent brain connectivity networks, but these features may not be well coordinated with subsequent classifiers. Besides, brain networks are often equipped with multiple hubs (i.e., nodes occupying a central position in the overall organization of a network), providing essential clues to describe connectivity patterns. However, existing studies often fail to explore such hubs from brain connectivity networks. To address these two issues, we propose a Connectivity Network analysis method with discriminative Hub Detection (CNHD) for brain disease diagnosis using functional magnetic resonance imaging (fMRI) data. Specifically, we incorporate both feature extraction of brain networks and network-based classification into a unified model, while discriminative hubs can be automatically identified from data via ℓ1-norm and ℓ2,1-norm regularizers. The proposed CNHD method is evaluated on three real-world schizophrenia datasets with fMRI scans. Experimental results demonstrate that our method not only outperforms several state-of-the-art approaches in disease diagnosis, but also is effective in automatically identifying disease-related network hubs in the human brain.

Modularity-Guided Functional Brain Network Analysis for Early-Stage Dementia Identification

“…Resting-state functional magnetic resonance imaging (rs-fMRI) provides a non-invasive measure of brain activity and attracts considerable attention for understanding the brain organization (Bijsterbosch et al, 2017 ; Zhang et al, 2020 ). Function brain network (FBN) derived from rs-fMRI scans has been increasingly employed to computer-aided diagnosis of brain disorders, such as autism spectrum disorder (Jie et al, 2018a ; Wang et al, 2019a , c ; Wen et al, 2019 ; He et al, 2020 ), Alzheimer's disease (AD) and its prodromal stage (i.e., mild cognitive impairment, MCI) (Stam, 2014 ; Fornito et al, 2015 ; Liu M. et al, 2015 ; Jie et al, 2018b ).…”

Dynamic functional connectivity analysis with temporal convolutional network for attention deficit/hyperactivity disorder identification

“…In contrast to previous studies that rely on pre-defined FC networks (e.g., via Pearson's correlation) (Wee et al, 2016;Jie et al, 2018;Wang et al, 2019aWang et al, , 2022, the proposed method can generate dynamic FC networks in a data-driven manner. We now investigated the FC networks constructed by the proposed TDNet in the KKI site.…”

Accurate Module Induced Brain Network Construction for Mild Cognitive Impairment Identification with Functional MRI

“…It has been reported that FBN generally has more topological structures than just sparsity (Meunier et al, 2009;Zhao et al, 2012;Sporns, 2016;Wang et al, 2019a;Wen et al, 2019). For example, one of the most representative structure is modularity that is believed to be extremely important for promoting stability, conserving wiring cost, and enabling complex neuronal dynamics of our brain.…”