Network biomarkers of schizophrenia by graph theoretical investigations of Brain Functional Networks
Brain Functional Networks (BFNs), graph theoretical models of brain activity data, provide a systems perspective of complex functional connectivity within the brain. Neurological disorders are known to have basis in abnormal functional activities, that could be captured in terms of network markers. Schizophrenia is a pathological condition characterized with altered brain functional state. We created weighted and binary BFN models of schizophrenia patients as well as healthy subjects starting from fMRI data in an effort to search for network biomarkers of the disease. We investigated 45 topological features of BFNs and their higher order combinations (2 to 8). We find that network features embodying modularity, betweenness, assortativity and edge density emerge as key markers of schizophrenia. Also, features derived from weighted BFNs were observed to be more effective in disease classification as compared to those from binary BFNs. These topological markers may provide insights into mechanisms of functional activity underlying disease phenotype and could further be used for designing algorithms for clinical diagnosis of schizophrenia as well as its early detection.
Code (0)
등록된 구현이 없습니다.
Tasks
Functional ConnectivitySimilar Papers 제목 키워드 기반
BrainIB++: Leveraging Graph Neural Networks and Information Bottleneck for Functional Brain Biomarkers in Schizophrenia
The development of diagnostic models is gaining traction in the field of psychiatric disorders. Recently, machine learning classifiers based on resting-state functional magnetic resonance imaging (rs-fMRI) have been deve…
Graph Neural NetworkFeature EngineeringNetMoST: A network-based machine learning approach for subtyping schizophrenia using polygenic SNP allele biomarkers
Subtyping neuropsychiatric disorders like schizophrenia is essential for improving the diagnosis and treatment of complex diseases. Subtyping schizophrenia is challenging because it is polygenic and genetically heterogen…
A Biologically Interpretable Graph Convolutional Network to Link Genetic Risk Pathways and Imaging Phenotypes of Disease
We propose a novel end-to-end framework for whole-brain and whole-genome imaging-genetics. Our genetics network uses hierarchical graph convolution and pooling operations to embed subject-level data onto a low-dimensiona…
feature selectionMulti-modal Dynamic Graph Network: Coupling Structural and Functional Connectome for Disease Diagnosis and Classification
Multi-modal neuroimaging technology has greatlly facilitated the efficiency and diagnosis accuracy, which provides complementary information in discovering objective disease biomarkers. Conventional deep learning methods…
Aberrant High-Order Dependencies in Schizophrenia Resting-State Functional MRI Networks
The human brain has a complex, intricate functional architecture. While many studies primarily emphasize pairwise interactions, delving into high-order associations is crucial for a comprehensive understanding of how fun…